© 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. 1328
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to legal terminology and proceedings

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

    references to queries or requests, particularly in a technical or programming context

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

    case management order dated

    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
     might
    -2.59
     maybe
    -2.47
     may
    -2.47
     possibly
    -2.38
     perhaps
    -2.36
    might
    -2.31
     mungkin
    -2.29
     Possibly
    -2.28
    maybe
    -2.27
     misschien
    -2.21
    POSITIVE LOGITS
     AssemblyCulture
    0.71
     препратки
    0.69
    kháu
    0.67
    就行
    0.62
     nahilalakip
    0.62
    acaktır
    0.60
    ContentAlignment
    0.59
    netinet
    0.57
    就好
    0.56
    <bos>
    0.55
    Activations Density 0.597%

    No Known Activations