© 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
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104905
    Prev
    Next
    INDEX
    Explanations

    terms related to social dynamics and interpersonal relationships

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     كومونز
    -0.60
    CppMethod
    -0.56
    webElementXpaths
    -0.53
    ftagPool
    -0.52
    VYMaps
    -0.51
     فريبيس
    -0.51
    stdc
    -0.47
    #+#
    -0.46
    athread
    -0.46
    endregion
    -0.46
    POSITIVE LOGITS
     phénomène
    0.47
     humanas
    0.43
     太郎
    0.41
     bienfaits
    0.40
     phénomènes
    0.39
     zdarma
    0.39
     personnage
    0.39
     fenómeno
    0.39
     adultes
    0.38
     cinéma
    0.38
    Activations Density 0.055%

    No Known Activations