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. 3-GEMMASCOPE-RES-16K
    6. 6240
    Prev
    Next
    INDEX
    Explanations

    references to code exports and user interface elements in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vegas
    -0.61
    Vegas
    -0.53
    vegas
    -0.53
     Meno
    -0.51
    ıları
    -0.48
     Kazan
    -0.48
    AutoField
    -0.47
    ریق
    -0.46
     camp
    -0.46
    getDrawable
    -0.46
    POSITIVE LOGITS
    exports
    4.00
     exports
    1.47
    Exports
    1.38
     Exports
    1.25
     kasarigan
    1.03
    migrationBuilder
    0.90
    imports
    0.82
     exportaciones
    0.82
    EXPORT
    0.78
    addContainerGap
    0.77
    Activations Density 0.084%

    No Known Activations