© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 3852
    Prev
    Next
    INDEX
    Explanations

    phrases related to roles and responsibilities within organizations or political contexts

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

    words and phrases describing someone's role, position, or responsibilities in an organization.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mergeFrom
    -0.36
     corrida
    -0.35
    Fazit
    -0.35
    áneos
    -0.34
     Biaya
    -0.34
     vinaigre
    -0.34
     craindre
    -0.34
     gwiazd
    -0.34
     cancelación
    -0.34
     biaya
    -0.34
    POSITIVE LOGITS
     role
    2.83
     roles
    2.70
     Roles
    2.36
     Role
    2.33
    role
    2.30
    Role
    2.23
    roles
    2.19
     ROLE
    2.19
     rôle
    2.11
    Roles
    2.06
    Activations Density 0.791%

    No Known Activations