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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 6462
    Prev
    Next
    INDEX
    Explanations

    patterns related to code structure and programming logic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     שוליים
    -0.64
     estekak
    -0.62
     PublicKey
    -0.52
    באנגלית
    -0.47
    heben
    -0.47
    érape
    -0.46
     חיצוניים
    -0.46
     معرف
    -0.46
     Wayback
    -0.46
     himo
    -0.46
    POSITIVE LOGITS
    mobileqq
    0.70
     %@",
    0.66
    NOPQRST
    0.66
    THISDAY
    0.65
    ={[
    0.65
    "){
    
    0.61
     ';
    
    0.61
    });*/
    0.60
    ")){
    
    0.60
     }}"></
    0.60
    Activations Density 0.072%

    No Known Activations