© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 6476
    Prev
    Next
    INDEX
    Explanations

    elements related to fashion and dress styles

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

    formal dresses

    np_acts-logits-general · gemini-2.0-flash

    ball gown and dress

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sudadera
    -0.55
     hoody
    -0.55
     tatuagens
    -0.53
     hoodies
    -0.51
     sudad
    -0.50
     KTP
    -0.50
     graffiti
    -0.49
    genossen
    -0.49
     barba
    -0.49
    kmale
    -0.48
    POSITIVE LOGITS
     ball
    0.77
     strapless
    0.75
     gown
    0.73
     prom
    0.73
     ballroom
    0.69
     crin
    0.69
     tulle
    0.68
     dress
    0.68
     evening
    0.67
     Gown
    0.66
    Activations Density 0.122%

    No Known Activations