© 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. 72903
    Prev
    Next
    INDEX
    Explanations

    references to agreements and negotiations between parties

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

    negotiating and making agreements

    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
     heapq
    -0.49
     CreateTagHelper
    -0.41
    ApiRequest
    -0.40
    usermodel
    -0.38
    QueryResult
    -0.37
    :+:
    -0.37
    iedenen
    -0.37
    ือง
    -0.37
    Personendaten
    -0.37
     congrès
    -0.36
    POSITIVE LOGITS
     mutually
    0.66
     agreed
    0.63
     timings
    0.60
     verbally
    0.60
     arrangements
    0.60
     agreeing
    0.59
     agreeable
    0.57
     agree
    0.54
     Arrangements
    0.54
     acord
    0.53
    Activations Density 0.038%

    No Known Activations