© 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
    7. Residual Stream - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 683
    Prev
    Next
    INDEX
    Explanations

    traits associated with shyness and social anxiety

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

    fear and shyness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngrx
    -0.38
     contas
    -0.31
     INTERESAR
    -0.30
     indisponible
    -0.29
     entendre
    -0.29
     informée
    -0.29
    artifactId
    -0.29
     sportif
    -0.28
    VersionUID
    -0.28
     localObject
    -0.28
    POSITIVE LOGITS
     nervousness
    0.74
     timid
    0.71
     shy
    0.70
     cowardice
    0.69
     Nervous
    0.69
     courage
    0.68
    Nervous
    0.68
     fears
    0.66
     nervous
    0.66
     terrified
    0.65
    Activations Density 0.029%

    No Known Activations