© 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 - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 6213
    Prev
    Next
    INDEX
    Explanations

    instances of social events or parties being referenced

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    MathML
    -0.35
     module
    -0.32
    modules
    -0.31
     GUARD
    -0.30
     pilot
    -0.30
     Ranger
    -0.29
     passers
    -0.29
     window
    -0.29
    module
    -0.29
     modules
    -0.29
    POSITIVE LOGITS
     dinner
    0.93
    Dinner
    0.91
     PARTY
    0.89
     party
    0.89
     banquet
    0.88
    PARTY
    0.87
     Dinner
    0.86
     RSVP
    0.84
    dinner
    0.84
    Party
    0.82
    Activations Density 0.183%

    No Known Activations