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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 38297
    Prev
    Next
    INDEX
    Explanations

    references to painting and coloring techniques

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

    paint and color

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.78
    Tikang
    -0.72
    featureID
    -0.69
    expandindo
    -0.69
     FetchType
    -0.69
    transQ
    -0.68
    ChildScrollView
    -0.68
    AddTagHelper
    -0.66
    يكب
    -0.65
     مشين
    -0.65
    POSITIVE LOGITS
     painted
    0.37
     paint
    0.36
     or
    0.35
    painted
    0.35
    Colored
    0.34
    colored
    0.32
     colored
    0.31
    Painted
    0.30
    Paint
    0.30
     Painted
    0.29
    Activations Density 0.009%

    No Known Activations