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. 13-GEMMASCOPE-RES-16K
    6. 10797
    Prev
    Next
    INDEX
    Explanations

    mentions of the UAE and related geographic or political entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Herrmann
    -0.79
     EXAMIN
    -0.71
    ә
    -0.70
     disponibilités
    -0.67
     Schreiber
    -0.66
    omla
    -0.63
    んご
    -0.62
     Huse
    -0.61
    Holz
    -0.60
    gese
    -0.59
    POSITIVE LOGITS
     Dib
    0.97
    asthan
    0.89
     pymongo
    0.89
     Rajasthan
    0.86
     Toul
    0.83
     Nasser
    0.83
     ureter
    0.82
     Kyr
    0.82
     Yuma
    0.82
    GeoNames
    0.81
    Activations Density 0.485%

    No Known Activations