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. 77208
    Prev
    Next
    INDEX
    Explanations

    special characters and symbols in code or strings

    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
    >--}}
    -0.60
    "]);
    
    -0.59
    ')){
    -0.53
    quelize
    -0.53
    _
    
    -0.52
    '));
    
    -0.51
    '>
    
    -0.51
    ']);
    
    -0.51
    ']){
    -0.51
     --}}
    -0.50
    POSITIVE LOGITS
    HomeAsUpEnabled
    0.64
     ſeveral
    0.63
     leſs
    0.63
    ("/
    0.57
     myſelf
    0.56
    ("
    0.56
     fufficient
    0.54
     itſelf
    0.54
     "<
    0.54
     "
    0.54
    Activations Density 0.034%

    No Known Activations