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. 997
    Prev
    Next
    INDEX
    Explanations

    occurrences of the keyword "const" particularly in programming contexts

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

    occurrences of the keyword "const" in code snippets

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

    const, override in code

    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
    >");
    
    -0.81
    )");
    
    -0.79
    "));
    
    -0.77
    "]);
    
    -0.77
    "];
    
    -0.75
    (");
    -0.74
    .");
    
    -0.71
    :");
    
    -0.68
    ")));
    
    -0.68
     ");
    
    -0.67
    POSITIVE LOGITS
    帖最后由
    0.68
     createState
    0.56
    TestingModule
    0.56
    壤
    0.50
     noexcept
    0.48
     onlyOwner
    0.47
    Lähteet
    0.46
    complexContent
    0.46
    Viitteet
    0.45
    rawDesc
    0.45
    Activations Density 0.005%

    No Known Activations