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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 8128
    Prev
    Next
    INDEX
    Explanations

    references to specific sneaker releases or models

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

    Footwear, especially sneakers and shoes

    np_acts-logits-general · gemini-2.0-flash

    sneakers and shoes

    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
    eseorang
    -0.47
    อาหาร
    -0.45
     alimentaire
    -0.43
     vectorielle
    -0.41
     realistas
    -0.41
     sexuelle
    -0.40
     contratar
    -0.39
     Económica
    -0.39
     nourriture
    -0.38
     effectiveness
    -0.38
    POSITIVE LOGITS
     sneaker
    0.75
     footwear
    0.72
     shoes
    0.71
     shoe
    0.64
     Shoes
    0.62
    AsUp
    0.62
    shoes
    0.60
    Shoes
    0.59
    styleType
    0.59
    yntaxException
    0.59
    Activations Density 0.058%

    No Known Activations