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. 91538
    Prev
    Next
    INDEX
    Explanations

    mention of female characters and their relationships

    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
     żyw
    -0.33
    aderos
    -0.31
    Garantía
    -0.31
     Formación
    -0.30
     możliwe
    -0.30
     Construcción
    -0.30
     gwaran
    -0.28
     pháp
    -0.28
     län
    -0.28
     îmb
    -0.28
    POSITIVE LOGITS
    UnitTesting
    0.62
     ModelExpression
    0.61
     neurotic
    0.58
    CppMethod
    0.57
    UrlResolution
    0.57
    MLLoader
    0.55
     '\\;'
    0.54
    tigem
    0.54
    $_['
    0.54
    Portály
    0.54
    Activations Density 0.035%

    No Known Activations