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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 16062
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to the act of painting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    Diwedd
    -0.53
    XmlSchema
    -0.53
     يتيمه
    -0.52
     nahilalakip
    -0.51
    saraba
    -0.51
    lewati
    -0.50
     nakalista
    -0.50
    Bris
    -0.50
    ganggu
    -0.50
     للمعارف
    -0.49
    POSITIVE LOGITS
     Paint
    1.14
    Paint
    1.09
     paint
    1.09
     painting
    1.00
    Painting
    0.99
     Painting
    0.99
     PAINT
    0.99
    PAINT
    0.95
    paint
    0.91
    painting
    0.90
    Activations Density 0.070%

    No Known Activations