© 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. 102393
    Prev
    Next
    INDEX
    Explanations

    symbols or placeholders indicating the end of a code block or statement

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

    container registry commands

    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
    tieg
    -0.33
    .*")]
    -0.31
    strahlung
    -0.29
     Reclamation
    -0.28
    dtype
    -0.27
     ſeveral
    -0.26
    телни
    -0.26
     Salvage
    -0.25
    ranslated
    -0.25
    krie
    -0.25
    POSITIVE LOGITS
    webElementXpaths
    0.79
     ویکی‌پدی
    0.73
    出版年
    0.71
    TypedDataSet
    0.69
    adaptiveStyles
    0.68
    ]")]
    0.68
    principalColumn
    0.67
    Personendaten
    0.67
    UnsafeEnabled
    0.66
     nahilalakip
    0.66
    Activations Density 0.036%

    No Known Activations