© 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. 9-GEMMASCOPE-RES-131K
    11. 51647
    Prev
    Next
    INDEX
    Explanations

    terminology related to the significance and impact of roles in various contexts

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

    playing a role

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Pautan
    -0.43
    mparas
    -0.40
     berke
    -0.39
     Roskov
    -0.38
     archivi
    -0.33
     duffel
    -0.33
     rasg
    -0.33
    Externe
    -0.32
     bicicletas
    -0.32
     Connectez
    -0.32
    POSITIVE LOGITS
     role
    0.80
     Role
    0.79
     ROLE
    0.74
    featureID
    0.70
    Role
    0.69
     роль
    0.68
    role
    0.63
     berperan
    0.63
     ruolo
    0.63
    ThemeOverlay
    0.61
    Activations Density 0.013%

    No Known Activations