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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 695
    Prev
    Next
    INDEX
    Explanations

    technical terms related to engineering and measurements

    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
    exitRule
    -0.60
    EDEFAULT
    -0.54
    fillType
    -0.54
     Meksiku
    -0.53
     يتيمه
    -0.52
    FunctionFlags
    -0.52
    Rüyada
    -0.52
    antaranya
    -0.51
     Италијани
    -0.49
    rungsseite
    -0.48
    POSITIVE LOGITS
     Alquiler
    0.36
    綢
    0.34
     beneficiaries
    0.32
    estacks
    0.31
     BorderSide
    0.31
     viſ
    0.31
    enaire
    0.31
     Redacción
    0.30
     useAppContext
    0.29
     tenda
    0.29
    Activations Density 0.192%

    No Known Activations