© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 81182
    Prev
    Next
    INDEX
    Explanations

    references to "bench" in various contexts, particularly in legal or evaluation settings

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    bench trial or conference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     total
    -0.39
     erwartet
    -0.39
     Mayr
    -0.38
    total
    -0.36
    Total
    -0.36
    物
    -0.36
     فقد
    -0.35
    ;'>
    -0.35
    IDAY
    -0.35
    })}
    -0.35
    POSITIVE LOGITS
     bench
    2.56
     Bench
    2.44
    Bench
    2.28
    bench
    2.27
     benches
    1.97
    BENCH
    1.73
    ベンチ
    1.57
     workbench
    1.27
     Benchmark
    1.16
     benchmarks
    1.13
    Activations Density 0.005%

    No Known Activations