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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 8581
    Prev
    Next
    INDEX
    Explanations

    instances of the word "draw" and its variations

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

    "drawing" or "drawn"

    np_acts-logits-general · gemini-2.0-flash

    drawing on or making connections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -0.75
     ambientales
    -0.67
     referenties
    -0.63
     /\.(
    -0.63
     AppComponent
    -0.60
     accett
    -0.58
     ambientale
    -0.58
     accepté
    -0.58
     fallu
    -0.57
    Skocz
    -0.56
    POSITIVE LOGITS
     drawn
    1.57
     draw
    1.52
     draws
    1.49
     drew
    1.47
     Draws
    1.47
     drawing
    1.45
     Draw
    1.42
     Drawing
    1.40
     Drawn
    1.37
     DRAW
    1.36
    Activations Density 0.148%

    No Known Activations