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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9-GEMMASCOPE-RES-16K
    6. 15387
    Prev
    Next
    INDEX
    Explanations

    references to color

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )");
    
    -1.44
    )";
    
    -1.27
     themſelves
    -1.25
    `;
    
    -1.24
     myſelf
    -1.24
    `,
    
    -1.23
    ]]
    
    -1.20
    makeConstraints
    -1.20
    "]);
    
    -1.18
    "]];
    -1.17
    POSITIVE LOGITS
     color
    1.45
    color
    1.44
     Color
    1.40
    Color
    1.37
     COLOR
    1.36
    COLOR
    1.36
     colors
    1.32
     Colors
    1.18
    colors
    1.13
     colores
    1.11
    Activations Density 0.039%

    No Known Activations