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

    Neuronpedia

    APICircuit 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. 11-GEMMASCOPE-RES-16K
    6. 6371
    Prev
    Next
    INDEX
    Explanations

    medical terms and concepts related to the esophagus and related procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wallflower
    -0.75
    BoxShadow
    -0.73
    布
    -0.71
    HtmlAttribute
    -0.71
     Brown
    -0.70
      
    -0.68
    yd
    -0.66
     abus
    -0.66
    ily
    -0.66
     [[
    -0.66
    POSITIVE LOGITS
     Estelle
    1.37
     Es
    1.34
     Esau
    1.26
     ES
    1.23
    Es
    1.21
     es
    1.20
     Esch
    1.19
     Esmeralda
    1.18
     Esposito
    1.16
     ESC
    1.05
    Activations Density 0.158%

    No Known Activations