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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 91499
    Prev
    Next
    INDEX
    Explanations

    instances of non-numeric characters and punctuation

    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
     AssemblyCompany
    -0.71
     للمعارف
    -0.66
    nloa
    -0.63
     MainAxisSize
    -0.63
    transQ
    -0.61
    OGND
    -0.60
    MigrationBuilder
    -0.60
    windowFixed
    -0.57
    
    -0.56
     defaultstate
    -0.56
    POSITIVE LOGITS
     matrícula
    0.40
    didSet
    0.32
    andler
    0.32
     Rest
    0.29
    Там
    0.29
     pê
    0.29
     pén
    0.29
     tackle
    0.29
     inscripción
    0.29
    Tack
    0.28
    Activations Density 0.014%

    No Known Activations