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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 1338
    Prev
    Next
    INDEX
    Explanations

    references to clothing and items being worn

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

    clothing items and articles of apparel that people wear.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     plasmids
    -0.39
     gine
    -0.37
     springfox
    -0.37
     plasmid
    -0.35
     poveznice
    -0.35
     tec
    -0.34
     marmor
    -0.33
     tenda
    -0.32
     curs
    -0.32
     Libro
    -0.30
    POSITIVE LOGITS
     wear
    1.79
     wearing
    1.77
     wearer
    1.69
     worn
    1.65
     Wearing
    1.63
     wears
    1.62
     wore
    1.61
    Wearing
    1.60
     Wear
    1.56
     indoss
    1.50
    Activations Density 0.279%

    No Known Activations