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. 7-GEMMASCOPE-RES-16K
    6. 8805
    Prev
    Next
    INDEX
    Explanations

    references to color and color-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )");
    
    -1.38
    makeConstraints
    -1.24
    Personensuche
    -1.20
    )";
    
    -1.18
    `,
    
    -1.17
    `;
    
    -1.13
    "]);
    
    -1.13
    BibitemShut
    -1.13
     myſelf
    -1.13
    ]]
    
    -1.11
    POSITIVE LOGITS
     color
    1.67
    color
    1.58
     colors
    1.56
     Color
    1.56
    Color
    1.55
     COLOR
    1.54
    COLOR
    1.44
     Colors
    1.36
    colors
    1.31
     colores
    1.29
    Activations Density 0.057%

    No Known Activations