© 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. 636
    Prev
    Next
    INDEX
    Explanations

    names and word endings that denote ethnic or cultural identities

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

    names or terms related to specific individuals or cultural references

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

    words ending in -ian

    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
    findpost
    -0.75
    InitVars
    -0.68
    مصادر
    -0.65
    曖昧さ回避
    -0.64
    getMinutes
    -0.63
    исленность
    -0.63
    ंदीखरीदारी
    -0.63
    AccessorTable
    -0.63
    ceq
    -0.63
    elesai
    -0.62
    POSITIVE LOGITS
    ism
    0.93
    apolis
    0.83
    izing
    0.72
    ity
    0.70
    dian
    0.66
    ità
    0.65
    lian
    0.64
    alysis
    0.62
    itet
    0.61
    ISM
    0.61
    Activations Density 0.106%

    No Known Activations