© 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. 20-GEMMASCOPE-RES-131K
    11. 116698
    Prev
    Next
    INDEX
    Explanations

    technical terms related to semiconductor technology and analytics

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

    patterns in technical contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    Демографія
    -0.36
    Aiheesta
    -0.34
    scriptcase
    -0.31
     ModelRenderer
    -0.30
    illy
    -0.30
     close
    -0.29
    tagHelperRunner
    -0.29
    archiviato
    -0.28
     dolay
    -0.28
    相當
    -0.28
    POSITIVE LOGITS
    aarrggbb
    0.66
    dafx
    0.62
    LabelTagHelper
    0.57
    netinet
    0.54
    CloseOperation
    0.53
    AntiForgeryToken
    0.50
    setPreferredSize
    0.50
     gameOver
    0.50
     handleClick
    0.50
    thâu
    0.50
    Activations Density 0.318%

    No Known Activations