© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 101635
    Prev
    Next
    INDEX
    Explanations

    keywords related to data handling and processing in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    migrationBuilder
    -0.71
     CanadaChoose
    -0.59
     الرياضيه
    -0.56
    UnusedPrivate
    -0.52
    Derbyniad
    -0.49
    ParallelGroup
    -0.49
     otomatig
    -0.48
     resourceCulture
    -0.47
    Попис
    -0.47
     CallOverrides
    -0.47
    POSITIVE LOGITS
     dAtA
    0.50
     članak
    0.47
    Gruss
    0.37
    లాలు
    0.36
    DataColumn
    0.35
    sert
    0.34
    aarrggbb
    0.33
     пун
    0.33
     ویکی‌پدی
    0.33
     saites
    0.33
    Activations Density 0.144%

    No Known Activations