© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 631
    Prev
    Next
    INDEX
    Explanations

    references to scientific journals or publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to scientific articles or publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Phys. Rev. citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.55
     entend
    -0.49
    webpack
    -0.48
    ymce
    -0.48
    odule
    -0.47
     Ambulance
    -0.46
     LUMP
    -0.45
    itten
    -0.45
     Town
    -0.45
    ounty
    -0.44
    POSITIVE LOGITS
    PhysRev
    0.92
    parsedMessage
    0.72
    ंदीखरीदारी
    0.69
    HideFlags
    0.68
    windowFixed
    0.67
     StatefulWidget
    0.62
    VIAF
    0.61
     мәкал
    0.60
     pinulongan
    0.60
    észetes
    0.59
    Activations Density 0.023%

    No Known Activations