© 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-2-9B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 11882
    Prev
    Next
    INDEX
    Explanations

    action-oriented words related to drawing or illustrating

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    ValueStyle
    -0.80
    RegressionTest
    -0.78
     EconPapers
    -0.69
    CppMethod
    -0.66
    Personensuche
    -0.61
     nahilalakip
    -0.59
    principalColumn
    -0.57
     Belf
    -0.56
     arşivlendi
    -0.54
    Identyfik
    -0.54
    POSITIVE LOGITS
     draw
    2.22
     drawing
    2.11
     Draw
    2.08
    Draw
    2.02
    draw
    2.02
     drawn
    1.91
     Drawing
    1.88
     DRAW
    1.88
     draws
    1.85
     drew
    1.80
    Activations Density 0.118%

    No Known Activations