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

    Neuronpedia

    Jacobian LensNEW
    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. 5-GEMMASCOPE-RES-16K
    11. 12493
    Prev
    Next
    INDEX
    Explanations

    instances of the word "paint" and variations of it related to the act of painting or the results of painting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     chaleco
    -0.72
    numRows
    -0.71
     Berwick
    -0.70
     mContext
    -0.70
     memberId
    -0.70
    اااا
    -0.69
    eseorang
    -0.68
    Према
    -0.68
     تضيفلها
    -0.67
    NavController
    -0.66
    POSITIVE LOGITS
     paint
    2.18
     PAINT
    2.13
     Paint
    2.13
     paints
    2.09
    paint
    2.09
     painting
    2.05
     painted
    2.03
    Paint
    1.92
    painted
    1.92
     Paints
    1.82
    Activations Density 0.037%

    No Known Activations