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. 20-GEMMASCOPE-RES-16K
    6. 12062
    Prev
    Next
    INDEX
    Explanations

    references to religious or saintly titles associated with places or institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     consultato
    -0.77
    IntoConstraints
    -0.76
     مشين
    -0.74
     незавершена
    -0.74
     متعلقه
    -0.69
    HtmlAttribute
    -0.67
    مصادر
    -0.67
    abestanden
    -0.66
     Wikimedijinoj
    -0.61
     kasarigan
    -0.61
    POSITIVE LOGITS
     John
    0.56
     Paul
    0.54
     lames
    0.48
     Luke
    0.47
    Paul
    0.47
     Mary
    0.46
     James
    0.46
    John
    0.46
     George
    0.45
     imprese
    0.43
    Activations Density 0.063%

    No Known Activations