© 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. 17081
    Prev
    Next
    INDEX
    Explanations

    concepts related to negotiations and agreements in political contexts

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

    international agreements and inspections

    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
     recently
    -0.37
     trying
    -0.36
    Mixin
    -0.35
    LookAnd
    -0.35
    联系
    -0.34
    AVAILABLE
    -0.34
    Available
    -0.32
     fark
    -0.32
     barely
    -0.32
     Anteil
    -0.31
    POSITIVE LOGITS
    DoubleQuotes
    0.67
     disarmament
    0.66
     utafitiHapana
    0.66
    tanleria
    0.65
    delwed
    0.64
     concessions
    0.62
     referenties
    0.62
     disarm
    0.60
    ilitar
    0.60
    agreed
    0.60
    Activations Density 0.045%

    No Known Activations