cs.LGMay 25, 2026

Geometric Evolution Maps: Extracting Stable Concept Probes from Transformer Residual Streams

Authors: James Henry

Organizations: Independent Researcher

Abstract

Concept probes extracted from transformer residual streams are only as reliable as the layer from which they are extracted. The common practice of probing at a fixed late layer or at the peak of a separation score function ignores a fundamental structural feature: concept representations undergo substantial directional rotation during their assembly phase, and do not settle into a stable direction until a characteristic handoff layer after the primary Concept Allocation Zone (CAZ). We introduce Geometric Evolution Maps (GEMs), which track the full directional trajectory of a concept through residual stream activations, identify the handoff layer where rotation ceases, and extract the settled probe direction from that layer. Across 23 architectures spanning 70M to 14B parameters and 17 concept types, the entry-to-exit cosine similarity within CAZs has a mean of 0.233, showing that probe direction at CAZ entry does not reliably predict probe direction at exit. Ablation experiments across 391 concept x model pairs (23 models x 17 concepts) show that GEM-extracted probes are at least as precise as peak-layer probes in 268/391 trials (68.5%), and strictly outperform in 259/391 (66.2%). The architecture split is pronounced: MHA models favour the handoff in 173/221 trials (78.3%); GQA models favour the handoff in only 56/119 trials (47.1%). Model-level Wilcoxon: W=214, N=23, p=0.010 (one-sided). An adaptive ablation width rule targets the 79/391 near-final-layer cases: it improves probe quality in 60/79 triggered cases (75.9%), mean gain +7.44pp. A direction-specificity control confirms the ablation effect is concept-direction specific: median 377x suppression rate versus random-direction ablation (99.1% of concept directions beat all 10 random seeds). Reference implementation: rosetta_tools v1.3.1 (doi:10.5281/zenodo.20361433).

Explore similar work

CardsList
May 24, 2026cs.LG

The Concept Allocation Zone: Tracking How Concepts Form Across Transformer Depth

Concept formation in transformer language models is depth-extended, not a single-layer event: concepts emerge gradually across a contiguous region of the residual stream. Mechanistic interpretability methods identify the single layer of peak class separation -- the "best layer" -- capturing a snapshot rather than the process itself. We introduce the Concept Allocation Zone (CAZ): the depth interval within which a concept becomes measurably separable, the region allocated to its geometric expression. We formalize the CAZ through three layer-wise metrics (Separation, Concept Coherence, Concept Velocity) and derive principled boundary detection without manual layer sweeps. A CAZ is not a concept: it is the depth region within which the model organizes its geometry to make a concept separable. A single concept typically participates in multiple CAZes; multiple concepts may share one. Empirical validation across 34 models from 8 architectural families and 7 concepts reveals that the separation curve S(l) is frequently multimodal. A scored detector uncovers "gentle CAZes" -- subtle allocation regions invisible to standard peak detection but causally active in 93-100% of cases under ablation (16 of 34 models; 26 in the companion validation paper). The framework generates seven testable predictions; four yield clear verdicts (two not supported, one partially supported, one supported), one had its precondition invalidated by the data, and two are underpowered -- with cross-architecture alignment confirmed as depth-matched rather than monolithic under leave-one-concept-out cross-validation. Reference implementation: rosetta_tools v1.3.1 (doi:10.5281/zenodo.20361433).
James Henry
Transformer VariantConcept Bottleneck ModelsModel ActivationsProtein Language ModelMechanistic InterpretabilitySource Separation+1
AskPDF
May 2, 2026cs.LG

Concepts Whisper While Syntax Shouts: Spectral Anti-Concentration and the Dual Geometry of Transformer Representations

We test whether the causal inner product of \citet{park2024linear} -- defined by the unembedding covariance ΣΣ -- enables cross-lingual concept transport. Across 17 models and 4 language pairs, a matched-spectrum randomization test finds that Whitened Causal Alignment is indistinguishable from spectral regularization alone (p=0.95p = 0.95). However, this failure reveals a broader phenomenon: anti-concentration is observed in residual-stream difference-of-means vectors across five architecture families (p<10−33p < 10^{-33}) and supported by SAE features (e.g., p=4.5×10−19p = 4.5 \times 10^{-19}) and linear probes on Gemma and Llama. We discover a \emph{dual geometry}: activation-space concept directions anti-concentrate in the spectral tail, while static unembedding-row contrasts \emph{concentrate} in high-variance directions (p<10−4p < 10^{-4}). Split-injection causal interventions support the functional basis on Gemma and Llama (Cohen's dd up to 1.801.80), and POS-tag probing across 8 models shows syntax preferentially encodes in the high-variance subspace in 6 of 8 architectures (p<0.013p < 0.013), with the Qwen~2.5 family showing a significant reversal consistent with architecture-specific spectral structure. These results suggest transformers may rotate semantic content into spectrally quiet regions during contextualized processing, encoding concepts where they can be manipulated with reduced grammatical disruption.
Pratyush Acharya, Nuraj Rimal, Habish Dhakal
Geometric ReasoningConcentration Inequalities
AskPDF
Jul 20, 2026cs.LG

An Analysis of Residual-Stream Geometry Across Transformer Depth

We propose a transition-centred geometric analysis of transformer residual streams. Relative displacement measures how \emph{far} representations move between consecutive layers, and orthogonal Procrustes analysis separates each transition into a rigid rotation and a non-rigid residual. Across six instruction-tuned models, on code generation and cross-lingual translation, these measurements reveal reproducible depth regularities. Relative displacement is strongly layer-dependent; typically larger early and late, with a quieter middle third; and nearly invariant across conditions within each model. Rotation magnitude is nearly constant across depth, while Procrustes residual and angle concentration remain depth-modulated, with residual peaking at the final transition. During generation, non-English targets show larger final-layer displacement and residual than English targets. We present these as descriptive geometric regularities, not as measures of computational effort or causal explanations. The contribution is a measurement framework for residual-stream transitions and evidence that, in the settings studied here, depth curves are model-dependent and largely condition-stable.
Sunit Bhattacharya, Ravi Shankar Kolli
Transformer Residual StreamsResidual StreamSearch DepthVisual Geometry Grounded TransformerDiffusion TransformersGeometric Reasoning+1
AskPDF