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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 131041
    Prev
    Next
    INDEX
    Explanations

    content related to social justice and historical narratives about race

    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
    Tikang
    -0.42
     Himo
    -0.42
    astéroïdes
    -0.41
     enfans
    -0.40
    arschijnlijk
    -0.37
    agaimana
    -0.36
     obispo
    -0.36
     arşivlendi
    -0.36
    IsMutable
    -0.35
    مقاله
    -0.35
    POSITIVE LOGITS
     MainAxisSize
    0.57
     pinulongan
    0.56
    ollectionView
    0.54
    Diwedd
    0.53
     createSlice
    0.51
    >>();
    0.47
     
    0.47
    )]);
    0.45
    UnusedPrivate
    0.45
     fucking
    0.45
    Activations Density 0.018%

    No Known Activations