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. 45511
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific data types, especially in technical contexts

    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
     aapt
    -0.35
    <eos>
    -0.33
    Externí
    -0.30
    Nh
    -0.29
     Numerade
    -0.28
    import
    -0.28
    package
    -0.28
    tagPool
    -0.28
     teams
    -0.28
     lavar
    -0.27
    POSITIVE LOGITS
    IntoConstraints
    0.78
     nakalista
    0.65
     パンチラ
    0.65
     وتسجيلات
    0.65
    <unused79>
    0.64
    <unused8>
    0.64
    <unused41>
    0.63
    <unused52>
    0.63
    <unused14>
    0.63
    [@BOS@]
    0.63
    Activations Density 0.030%

    No Known Activations