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. 5958
    Prev
    Next
    INDEX
    Explanations

    numerical references and symbolic annotations in religious texts

    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
    ở
    -0.61
    "]}
    -0.59
    htdocs
    -0.59
    LEGGI
    -0.54
    --;
    
    -0.54
     "];
    -0.54
    PROMOTED
    -0.54
    Atentamente
    -0.53
    RefNanny
    -0.53
     مرئيه
    -0.53
    POSITIVE LOGITS
     courriel
    0.70
     CURIAM
    0.69
     <<<<<<<<<<<<<<
    0.68
     nuages
    0.63
     giudi
    0.59
     vectorielles
    0.59
    CloseOperation
    0.58
     Paglinawan
    0.57
     avoient
    0.56
     chrétien
    0.55
    Activations Density 0.089%

    No Known Activations