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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 6307
    Prev
    Next
    INDEX
    Explanations

    instructions related to makeup application techniques, particularly for eyebrow grooming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     surla
    -0.70
    AnchorStyles
    -0.58
     ArrayAdapter
    -0.56
     MainAxisSize
    -0.54
    {?>
    -0.53
    setVerticalGroup
    -0.52
     république
    -0.50
    UnusedPrivate
    -0.50
    boten
    -0.49
    🏀
    -0.49
    POSITIVE LOGITS
     makeup
    1.17
     Makeup
    1.04
    makeup
    1.03
    Makeup
    0.99
     lipstick
    0.98
     eyeshadow
    0.98
     eyeliner
    0.92
     mascara
    0.86
     cosmetics
    0.86
     Cosmetics
    0.81
    Activations Density 0.046%

    No Known Activations