Near-OOD Detection on SNIPS
97.98AUROCGemma2-9b LR baseline
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| Gemma2-9b LR baselineBackbone=Gemma2-9b, Detection Backend=Logistic Regression baseline, Evaluation Protocol=ID-only training2026.05 | 97.98 | 95.46 | 8.73 | |
| Gemma2-2b LR baselineBackbone=Gemma2-2b, Detection Backend=Logistic Regression baseline, Evaluation Protocol=ID-only training2026.05 | 97.46 | 94.23 | 15.28 | |
| Gemma2-2b + 16k SAE + MarkovBackbone=Gemma2-2b, SAE Configuration=16k, Detection Backend=Markov, Evaluation Protocol=ID-only training2026.05 | 96.99 | 93.38 | 15.25 | |
| Gemma2-9b + 16k SAE + MarkovBackbone=Gemma2-9b, SAE Configuration=16k, Detection Backend=Markov, Evaluation Protocol=ID-only training2026.05 | 90.01 | 82.87 | 31.5 |