© 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. 649
    Prev
    Next
    INDEX
    Explanations

    the name "Jean" and its variations in association with various contexts

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

    the name "Jean" and its variations in the context of references to individuals

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

    names like Jean

    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
    DockStyle
    -0.61
    IBOutlet
    -0.60
     ligiloj
    -0.57
     chimique
    -0.57
    nestjs
    -0.55
    सन्दर्भ
    -0.54
    LikeLike
    -0.54
    moveToFirst
    -0.52
    IndentedString
    -0.51
     esterni
    -0.50
    POSITIVE LOGITS
    nette
    0.83
    GraphicsUnit
    0.74
    apatilla
    0.59
    }}.
    0.59
     للمعارف
    0.58
    zeitig
    0.56
    protoc
    0.56
    IMS
    0.56
    ;">
    0.55
     StringTokenizer
    0.55
    Activations Density 0.008%

    No Known Activations