© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 68525
    Prev
    Next
    INDEX
    Explanations

    specific types of color descriptors or visual elements

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

    crayon colors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    /*
    -0.45
     Hoffmann
    -0.42
     Vuitton
    -0.41
     Hoffman
    -0.41
     Hof
    -0.41
    <sub>
    -0.41
     …
    -0.41
     Lipa
    -0.41
     Boba
    -0.40
    PreExecute
    -0.40
    POSITIVE LOGITS
     Cray
    2.42
    Cray
    2.27
     crayons
    2.05
     crayon
    2.03
    cray
    1.92
     cray
    1.70
     crayfish
    1.36
    🖍
    0.89
     lápiz
    0.81
     Pencil
    0.80
    Activations Density 0.000%

    No Known Activations