© 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. 27055
    Prev
    Next
    INDEX
    Explanations

    elements related to user interface components and navigation structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    tabs and tab bars

    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
    Not in Any Lists

    No Comments

    Negative Logits
    épendance
    -0.34
     ejemplares
    -0.33
     inappropriés
    -0.33
     teki
    -0.32
     regler
    -0.32
     ejemplos
    -0.30
    ukseen
    -0.29
    ysław
    -0.29
     reproducir
    -0.29
    InSection
    -0.28
    POSITIVE LOGITS
     ModelExpression
    0.70
     onCreateView
    0.64
    tabPage
    0.63
    writeField
    0.62
     tabPage
    0.62
    SourceChecksum
    0.59
     ویکی‌پدی
    0.59
    TabLayout
    0.59
    httphttps
    0.59
     pinulongan
    0.58
    Activations Density 0.022%

    No Known Activations