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. 15-GEMMASCOPE-RES-16K
    6. 5180
    Prev
    Next
    INDEX
    Explanations

    instances of the word "draw" and its variations, indicating a focus on actions related to drawing or attracting attention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     antemano
    -0.68
    EndProject
    -0.67
     ambientales
    -0.66
     Schulte
    -0.64
    IsContent
    -0.64
    /**
    -0.63
    globalData
    -0.61
    ️
    -0.61
     inoxydable
    -0.59
    poved
    -0.58
    POSITIVE LOGITS
     drawn
    1.71
     Drawn
    1.52
     Draws
    1.48
     draw
    1.47
     draws
    1.46
     drew
    1.45
     drawing
    1.44
    drawn
    1.42
     Draw
    1.37
    Drawn
    1.35
    Activations Density 0.081%

    No Known Activations