© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 81120
    Prev
    Next
    INDEX
    Explanations

    references to organizations and entities related to governance and operations within specific locales

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    managed, administered, operated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Negative Logits
    mulos
    -0.40
    esModule
    -0.37
    flashdata
    -0.37
    skrä
    -0.36
     scel
    -0.36
     gezin
    -0.35
    atting
    -0.33
    berapa
    -0.33
     scissor
    -0.33
    racht
    -0.33
    POSITIVE LOGITS
     managed
    1.25
     administered
    1.19
     administ
    1.19
     operated
    1.16
    managed
    1.12
     manages
    1.09
     manage
    1.05
    管理
    1.05
     administer
    1.05
     management
    1.02
    Activations Density 0.130%

    No Known Activations