Skip to content
SN-X
All research
PaperFebruary 21, 2026

The Geometry of Representations in Deep Networks

We study the intrinsic dimension and curvature of learned representations across 47 pre-trained models. We find a robust phase transition in representation geometry at the same scale where downstream capabilities begin to appear — and show that this transition is preceded by a measurable signal in the spectrum of the representation operator.

S. HaddadSN-XM. LindqvistY. ParkSN-X
View on arXiv

Question

Do representations undergo a qualitative change in geometry at the scale where new capabilities emerge, or is the transition smooth?

Method

We compute persistent homology and effective dimension profiles across training checkpoints for 47 pre-trained models spanning four orders of magnitude in parameter count.

Findings

  • Below a critical scale (≈ 6B parameters), representations are topologically

trivial — essentially a low-dimensional manifold.

  • Above the scale, a second cohomology class appears, persists across fine-tunes,

and predicts downstream capability gains (ρ = 0.78 with held-out evals).

  • The transition is *sharp* — a 1.4× increase in compute changes the topological

signature by more than 0.5σ.

Implication

Capability may not be a smooth function of scale after all. The data are consistent with a phase transition, and the order parameter is geometric.