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-2-2B
    4. Residual Stream - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 1109
    Prev
    Next
    INDEX
    Explanations

    the beginning of a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the beginning of the document or text segments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    conservatism walk

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    featureID
    -0.89
    `;
    
    -0.74
     doInBackground
    -0.69
     betweenstory
    -0.69
    '){
    
    -0.69
    "){
    
    -0.67
    uxxxx
    -0.66
    Filmografie
    -0.66
    `,
    
    -0.66
    __':
    
    -0.63
    POSITIVE LOGITS
    //
    0.62
    <b>
    0.53
     Theodo
    0.52
    tagHelperRunner
    0.48
    <strong>
    0.48
    dostęp
    0.46
    Cler
    0.46
     tık
    0.43
     Warming
    0.43
     akti
    0.43
    Activations Density 0.001%

    No Known Activations