© 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. 547
    Prev
    Next
    INDEX
    Explanations

    phrases related to licenses and terms of use

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

    references to legal language and disclaimers

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

    terms with mathematical expressions

    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
    class
    -0.53
    ždy
    -0.53
    łbym
    -0.48
    начально
    -0.46
     class
    -0.45
     then
    -0.45
     home
    -0.44
    home
    -0.43
    łby
    -0.43
    欠
    -0.43
    POSITIVE LOGITS
    principalColumn
    0.86
    NOPQRST
    0.79
    ContextHolder
    0.79
    XmlAccessType
    0.78
    WebElementEntity
    0.73
    zzleHttp
    0.71
    ScopeManager
    0.71
     becauſe
    0.71
    extAlignment
    0.70
    matchCondition
    0.69
    Activations Density 0.059%

    No Known Activations