List your company

Out-of-Distribution Detection on 20NG (ID) vs IMDB (OOD)

99.78AUROCGemma2-2b LR baseline
91.387293.566195.74597.9239May 12, 2026

Evaluation results

MethodLinks
Gemma2-2b LR baselineBackbone=Gemma2-2b, Backend=Logistic Regression, Training Protocol=ID-only training2026.0599.7899.920.72
Gemma2-9b LR baselineBackbone=Gemma2-9b, Backend=Logistic Regression, Training Protocol=ID-only training2026.0599.4598.41.7
Gemma2-9b + 16k SAE + MarkovBackbone=Gemma2-9b, SAE Size=16k, Backend=Markov, Training Protocol=ID-only training2026.0595.495.4433.61
Gemma2-2b + 16k SAE + MarkovBackbone=Gemma2-2b, SAE Size=16k, Backend=Markov, Training Protocol=ID-only training2026.0591.7190.5862.43