Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 35398
    Prev
    Next
    INDEX
    Explanations

    references to dressing or attire

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

    dress up in

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    ніципалі
    -0.55
     pinulongan
    -0.52
    EndProject
    -0.52
    principalColumn
    -0.48
     հղումներ
    -0.47
     endforeach
    -0.47
    ganggu
    -0.46
    UTERS
    -0.46
    astéroïdes
    -0.46
    astéro
    -0.45
    POSITIVE LOGITS
     dressed
    0.79
    dressed
    0.69
     DRESS
    0.65
     clothed
    0.64
    Dress
    0.64
     dressing
    0.62
     dress
    0.59
     Dressed
    0.57
    打扮
    0.57
     Dress
    0.57
    Activations Density 0.009%

    No Known Activations