List your company

Steering effectiveness correlation analysis on Gemma-2-2B concept families (across 26 layers)

0.871Correlation (rho) Alin vs delta PDifference-of-means steering
0.712920.753960.7950.83604Apr 16, 2026

Evaluation results

MethodLinks
Difference-of-means steeringFamily=Word transform, Model=Gemma-2-2B, Number of Layers=262026.040.871-0.7440.80910
Difference-of-means steeringFamily=Analogy, Model=Gemma-2-2B, Number of Layers=262026.040.866-0.9230.6470.001
Difference-of-means steeringFamily=Sequence, Model=Gemma-2-2B, Number of Layers=262026.040.814-0.830.86910
Difference-of-means steeringFamily=Pooled (n = 130), Model=Gemma-2-2B, Number of Layers=262026.040.777-0.7060.50710
Difference-of-means steeringFamily=Geography, Model=Gemma-2-2B, Number of Layers=262026.040.758-0.7290.3720.067
Difference-of-means steeringFamily=Arithmetic, Model=Gemma-2-2B, Number of Layers=262026.040.719-0.990.68810