Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 18-GEMMASCOPE-RES-16K
    6. 10097
    Prev
    Next
    INDEX
    Explanations

    punctuation marks used in dialogue and quotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Архівовано
    -0.56
     GenerationType
    -0.49
     jsonify
    -0.46
    jewództ
    -0.45
    zzleHttp
    -0.44
    yntaxException
    -0.43
    orros
    -0.43
    UIControlState
    -0.42
    štění
    -0.42
    figsize
    -0.42
    POSITIVE LOGITS
    LookAnd
    1.00
    IUrlHelper
    0.80
    )];
    
    0.79
    )]);
    0.78
    %");
    0.74
    >");
    
    0.73
    "));
    
    0.73
     AssemblyCulture
    0.71
    '));
    
    0.70
    ");
    
    0.69
    Activations Density 0.065%

    No Known Activations