© 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. 15202
    Prev
    Next
    INDEX
    Explanations

    phrases indicating interpersonal relationships and social interactions

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

    lacks or fails

    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
    なくても
    -0.32
    无可
    -0.32
     surla
    -0.32
    不需要
    -0.31
    ówno
    -0.31
     chauss
    -0.29
    无需
    -0.29
    enhanced
    -0.29
     خواهیم
    -0.28
    没事
    -0.28
    POSITIVE LOGITS
     Worse
    0.85
    Worse
    0.84
     دچار
    0.82
     suffers
    0.78
     worse
    0.76
     lacks
    0.76
     inability
    0.75
     fails
    0.75
     terlalu
    0.75
     suffer
    0.73
    Activations Density 0.103%

    No Known Activations