© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 21393
    Prev
    Next
    INDEX
    Explanations

    expressions of anxiety and concern about personal safety and privacy

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

    worry fear concern danger

    np_acts-logits-general · gemini-2.5-flash-lite

    sentences expressing personal worry, anxiety, or concern (first-person emotional statements).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     calcetines
    -0.53
     Inscrivez
    -0.52
     escolares
    -0.49
     sécurisé
    -0.49
     respiración
    -0.48
     communautaire
    -0.47
     Universitaria
    -0.46
     burbujas
    -0.45
    ercito
    -0.44
     Púb
    -0.44
    POSITIVE LOGITS
    TypedDataSet
    0.56
    UserScript
    0.51
    AddTagHelper
    0.46
    MigrationBuilder
    0.41
    GraphicsUnit
    0.40
     незавершена
    0.40
     برانيه
    0.40
     defaultstate
    0.38
    IsMutable
    0.37
    inqu
    0.37
    Activations Density 0.028%

    No Known Activations