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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 12702
    Prev
    Next
    INDEX
    Explanations

    phrases related to fashion and clothing preferences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MenuInflater
    -0.59
     köpek
    -0.55
     toolStrip
    -0.53
     greed
    -0.52
    intang
    -0.51
     PyQt
    -0.51
    SizeMode
    -0.51
    distribute
    -0.50
    prehension
    -0.50
     Distribution
    -0.50
    POSITIVE LOGITS
     casual
    0.90
     wardrobe
    0.88
     accessor
    0.84
     style
    0.82
     styled
    0.80
     outfit
    0.80
     outfits
    0.80
     looks
    0.77
     styles
    0.76
     styling
    0.75
    Activations Density 0.107%

    No Known Activations