© 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-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 213
    Prev
    Next
    INDEX
    Explanations

    terms related to clothing and fashion descriptions

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

    Types or features of dresses/clothing

    np_acts-logits-general · gemini-2.0-flash

    dress and clothing items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Behör
    -0.50
     Unterscheidung
    -0.48
    }))
    
    -0.47
     supplies
    -0.44
     SUPPLIES
    -0.44
     Supplies
    -0.44
     giudi
    -0.43
    niosek
    -0.42
    guantes
    -0.41
     Seguro
    -0.41
    POSITIVE LOGITS
     dress
    0.55
    WebServlet
    0.51
     blouse
    0.49
     drape
    0.48
     fashion
    0.48
     harem
    0.47
     Dress
    0.47
    dress
    0.47
     tunic
    0.47
     embellished
    0.47
    Activations Density 0.093%

    No Known Activations