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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 3694
    Prev
    Next
    INDEX
    Explanations

    properties and attributes related to colors and styles in visual elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "color" or "colour"

    np_acts-logits-general · gemini-2.0-flash

    color and colors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    assin
    -0.52
    się
    -0.49
     общество
    -0.49
    Referências
    -0.49
    ']))
    -0.48
    endpush
    -0.48
     Society
    -0.47
    }}^{(
    -0.47
    execSQL
    -0.46
     autorytatywna
    -0.46
    POSITIVE LOGITS
     color
    3.25
    color
    2.97
     Color
    2.78
    Color
    2.68
     colour
    2.54
     COLOR
    2.48
    COLOR
    2.22
     colors
    2.12
     Colour
    2.10
    colour
    2.04
    Activations Density 0.128%

    No Known Activations