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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14911
    Prev
    Next
    INDEX
    Explanations

    details related to footwear and their features

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

    Types of footwear

    np_acts-logits-general · gemini-2.0-flash

    footwear and shoes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     уро
    -0.48
    mybatisplus
    -0.43
    IContainer
    -0.40
    VersionUID
    -0.40
    WriteTagHelper
    -0.39
    }`).
    -0.39
    )_/¯
    -0.39
    Hosting
    -0.39
    }}">
    -0.38
    뀐
    -0.38
    POSITIVE LOGITS
     shoes
    1.03
     shoe
    1.01
     footwear
    0.95
     Shoes
    0.93
    shoes
    0.91
    shoe
    0.89
     Shoe
    0.88
     SHOES
    0.88
    Shoe
    0.87
    Shoes
    0.87
    Activations Density 0.158%

    No Known Activations