© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 10723
    Prev
    Next
    INDEX
    Explanations

    terms related to color and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    makeConstraints
    -0.99
    )");
    
    -0.96
    `,
    
    -0.96
    `;
    
    -0.91
    ihnachten
    -0.91
    Geplaatst
    -0.87
    """.
    -0.83
    {}'.
    -0.83
    anskje
    -0.82
    Viitteet
    -0.81
    POSITIVE LOGITS
     color
    2.35
     Color
    2.16
    color
    2.15
     COLOR
    2.12
     colors
    2.07
    Color
    2.06
    COLOR
    1.96
     colour
    1.90
     Colors
    1.81
    colors
    1.73
    Activations Density 0.041%

    No Known Activations