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. 6-GEMMASCOPE-RES-16K
    6. 9776
    Prev
    Next
    INDEX
    Explanations

    references to string manipulation and data processing in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GraphicsUnit
    -0.94
     Мексичка
    -0.90
    addCriterion
    -0.88
    RenderAtEndOf
    -0.82
    الإنجليزية
    -0.81
    ChildScrollView
    -0.75
     RouterModule
    -0.72
    LEncoder
    -0.72
     Ghi
    -0.68
     /\.(
    -0.67
    POSITIVE LOGITS
    wieś
    0.49
     بيها
    0.49
     McCall
    0.49
     تجاه
    0.48
    cipar
    0.48
    toFixed
    0.48
     sujeito
    0.48
     +=
    0.48
     $+
    0.47
     terdekat
    0.47
    Activations Density 0.028%

    No Known Activations