Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 9324
    Prev
    Next
    INDEX
    Explanations

    words related to jackets and coats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.66
    Insee
    -0.63
    lawayo
    -0.61
    :✨
    -0.60
    Демографія
    -0.58
    RTRS
    -0.58
     initComponents
    -0.58
    kkue
    -0.57
    躇
    -0.56
    enseits
    -0.55
    POSITIVE LOGITS
     jacket
    3.00
     Jacket
    2.65
     jackets
    2.60
     coat
    2.47
     coats
    2.33
    Jacket
    2.27
     Coat
    2.20
    jacket
    2.13
     Jackets
    1.96
    coat
    1.91
    Activations Density 0.109%

    No Known Activations