© 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. 12-GEMMASCOPE-RES-16K
    6. 12489
    Prev
    Next
    INDEX
    Explanations

    references to footwear and clothing items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ьаж
    -0.48
    abbix
    -0.43
    :✨
    -0.40
     poveznice
    -0.39
    gameserver
    -0.38
     лист
    -0.37
     חיצוניים
    -0.37
    PostConstruct
    -0.36
    渠
    -0.36
    xFFFFFF
    -0.35
    POSITIVE LOGITS
     shoes
    1.48
     Shoes
    1.33
     shoe
    1.31
     footwear
    1.27
     SHOES
    1.24
    shoes
    1.23
    Shoes
    1.23
     Shoe
    1.16
     Schuhe
    1.11
    shoe
    1.08
    Activations Density 0.191%

    No Known Activations