© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1901
    Prev
    Next
    INDEX
    Explanations

    terms related to style and elegance in fashion or design

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

    describing stylishness or sophistication

    np_acts-logits-general · gemini-2.0-flash

    style and elegance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    Not in Any Lists

    No Comments

    Negative Logits
     JpaRepository
    -0.39
     postIndex
    -0.38
    hyrchwyd
    -0.37
     Transfermarkt
    -0.36
    crollView
    -0.35
    xfb
    -0.35
     petition
    -0.34
     broadcast
    -0.34
     GoFundMe
    -0.33
     трав
    -0.33
    POSITIVE LOGITS
     elegant
    0.92
    elegant
    0.90
    Elegant
    0.87
     Elegant
    0.87
     elegante
    0.83
     stylish
    0.83
     chic
    0.82
     elegancia
    0.82
     elegan
    0.81
     elegance
    0.81
    Activations Density 0.099%

    No Known Activations