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. 0-GEMMASCOPE-RES-16K
    6. 6400
    Prev
    Next
    INDEX
    Explanations

    references to Microsoft-related entities and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ."));
    -0.95
     Efq
    -0.95
    DockStyle
    -0.90
     Roskov
    -0.89
    '));
    
    -0.89
    )";
    
    -0.88
    ']>;
    -0.87
    '])){
    
    -0.86
    )");
    
    -0.84
    `;
    
    -0.83
    POSITIVE LOGITS
     within
    0.86
     Within
    0.85
    Within
    0.82
    within
    0.76
     dentro
    0.73
    Microsoft
    0.68
     Microsoft
    0.63
     Dentro
    0.63
     WITHIN
    0.63
     Dalam
    0.62
    Activations Density 0.269%

    No Known Activations