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. 5-GEMMASCOPE-RES-16K
    6. 1619
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "draw" and its variations

    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
     inoxydable
    -1.02
    EndInit
    -0.93
     Schulte
    -0.87
    Collegamenti
    -0.87
     démission
    -0.80
    ParallelGroup
    -0.79
     modalités
    -0.78
    IContainer
    -0.78
    ContentAsync
    -0.77
    enderror
    -0.77
    POSITIVE LOGITS
     draw
    2.40
     drawn
    2.30
     draws
    2.27
    draw
    2.27
     Draw
    2.25
    Draw
    2.24
     Draws
    2.16
     DRAW
    2.15
     drawing
    2.14
     drew
    2.02
    Activations Density 0.041%

    No Known Activations