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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 13-GEMMASCOPE-RES-16K
    6. 13068
    Prev
    Next
    INDEX
    Explanations

    instances of the word "draw" or its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     inoxydable
    -0.99
    ContentAsync
    -0.87
    enderror
    -0.83
    ngdoc
    -0.82
    lepší
    -0.82
    +#+#
    -0.81
    EndProject
    -0.79
    Collegamenti
    -0.77
    ilene
    -0.77
    ptonshire
    -0.77
    POSITIVE LOGITS
     drawn
    1.58
     Draws
    1.42
     draw
    1.40
     drawing
    1.40
    Draw
    1.40
     Drawn
    1.39
     draws
    1.39
     Draw
    1.38
    drawn
    1.34
     DRAW
    1.34
    Activations Density 0.059%

    No Known Activations