© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 7034
    Prev
    Next
    INDEX
    Explanations

    events and gatherings related to awards and celebrations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Events, galas, parties, and receptions

    np_acts-logits-general · gemini-2.0-flash

    Gala dinner reception party

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MathML
    -0.47
     Audiodateien
    -0.46
     Ranger
    -0.33
     substitution
    -0.32
     module
    -0.32
     Module
    -0.32
     modules
    -0.31
    دانشنامهٔ
    -0.31
    Module
    -0.31
     Guardian
    -0.30
    POSITIVE LOGITS
     dinner
    0.88
    Dinner
    0.86
     gala
    0.85
     banquet
    0.85
     Dinner
    0.84
     party
    0.82
     event
    0.79
     PARTY
    0.79
    PARTY
    0.76
    party
    0.75
    Activations Density 0.157%

    No Known Activations