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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 9283
    Prev
    Next
    INDEX
    Explanations

    fashion-related terms and concepts related to styling

    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
     köpek
    -0.58
    MenuInflater
    -0.52
    providedIn
    -0.52
     pinball
    -0.52
    SizeMode
    -0.51
    UnusedPrivate
    -0.51
     هيا
    -0.51
     cantos
    -0.50
     høre
    -0.49
    adesivo
    -0.49
    POSITIVE LOGITS
     fashion
    1.29
     wardrobe
    1.24
     Fashion
    1.14
     style
    1.11
    Fashion
    1.08
     styling
    1.05
    fashion
    1.05
     FASHION
    1.03
     styles
    1.03
     dress
    1.02
    Activations Density 0.181%

    No Known Activations