© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 8051
    Prev
    Next
    INDEX
    Explanations

    sections of the text that are empty or not containing any content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -0.85
    setVerticalGroup
    -0.76
    InitVars
    -0.75
    ItemBackground
    -0.74
    ConstraintMaker
    -0.74
    RenderAtEndOf
    -0.71
    LabelTagHelper
    -0.69
     mergeFrom
    -0.68
    AutoScaleMode
    -0.68
     Roskov
    -0.67
    POSITIVE LOGITS
    AddHtmlAttribute
    1.40
    
    1.31
    
    1.30
    IMPORTED
    0.97
     []:
    0.91
    ViewImports
    0.78
     AssemblyTitle
    0.73
    openqa
    0.71
     kasarigan
    0.70
    ">//
    0.68
    Activations Density 0.003%

    No Known Activations