© 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-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 9307
    Prev
    Next
    INDEX
    Explanations

    instances of the word "draw" and its variations, indicating a focus on artistic or creative processes

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

    "draw" and its inflections

    np_acts-logits-general · gemini-2.0-flash

    draw attention, conclusions, inspiration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fallu
    -0.74
     /\.(
    -0.73
     antemano
    -0.71
    EndProject
    -0.70
     Schulte
    -0.68
    ️
    -0.68
     OnInit
    -0.67
    IsContent
    -0.64
    queryInterface
    -0.63
    jupiter
    -0.63
    POSITIVE LOGITS
     drawn
    1.69
     Drawn
    1.50
     Draws
    1.45
     drawing
    1.43
     draws
    1.43
     drew
    1.42
     draw
    1.42
    drawn
    1.39
    Drawn
    1.39
     Drawing
    1.33
    Activations Density 0.061%

    No Known Activations