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. 38871
    Prev
    Next
    INDEX
    Explanations

    specific technical and scientific vocabulary related to biology and computing

    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
     يتيمه
    -0.85
    ConstraintMaker
    -0.80
     pinulongan
    -0.76
    postsleuth
    -0.69
    IVEREF
    -0.68
    رشف
    -0.68
    SharedCtor
    -0.65
     للمعارف
    -0.64
    findpost
    -0.63
    UserScript
    -0.63
    POSITIVE LOGITS
    <eos>
    0.55
    ↵
    0.51
    '
    0.50
    ’
    0.49
    ↵↵
    0.48
     bl
    0.44
     
    0.42
    <tbody>
    0.42
    ↵↵↵
    0.40
    //
    0.39
    Activations Density 0.039%

    No Known Activations