Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 38918
    Prev
    Next
    INDEX
    Explanations

    curly braces used in LaTeX formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     Chwiliwch
    -0.68
    ConstraintMaker
    -0.64
    tagHelperRunner
    -0.64
    MigrationBuilder
    -0.63
    transQ
    -0.61
     Infórmanos
    -0.61
    onAttach
    -0.60
     disambiguazione
    -0.58
     protoimpl
    -0.56
     defaultstate
    -0.55
    POSITIVE LOGITS
    oa̍t
    0.40
    orghini
    0.36
    有事
    0.33
     Eisen
    0.33
    cnpj
    0.32
    税込
    0.32
    irsch
    0.31
     Geburt
    0.31
    testid
    0.31
     debt
    0.30
    Activations Density 0.000%

    No Known Activations