© 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. 13564
    Prev
    Next
    INDEX
    Explanations

    syntax elements or formatting indicators within a code snippet

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

    results, dual

    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
     Ecke
    -0.37
    ksjoner
    -0.32
     Boden
    -0.30
    Household
    -0.30
     cuchar
    -0.30
     household
    -0.29
    VersionUID
    -0.29
     especially
    -0.29
    BeforeMethod
    -0.28
    læg
    -0.28
    POSITIVE LOGITS
     result
    1.60
     results
    1.52
    result
    1.37
     Result
    1.35
    results
    1.34
     resultado
    1.31
     resultados
    1.29
     RESULT
    1.28
     Results
    1.28
    結果
    1.27
    Activations Density 0.060%

    No Known Activations