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. 8914
    Prev
    Next
    INDEX
    Explanations

    file and document structure elements, particularly in programming or markup contexts

    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
    webElementXpaths
    -0.80
    Искәрмәләр
    -0.77
    oredCriteria
    -0.72
    хьтан
    -0.69
    windowFixed
    -0.69
     AssemblyCulture
    -0.68
     mergeFrom
    -0.67
    Personendaten
    -0.66
     estekak
    -0.63
    Билгалдахарш
    -0.62
    POSITIVE LOGITS
    mn
    0.62
    IGraphics
    0.52
     XNUMX
    0.51
     пы
    0.49
     GenerationType
    0.49
     pymongo
    0.48
     Mure
    0.47
    gypti
    0.47
     Theses
    0.47
     Olms
    0.47
    Activations Density 0.028%

    No Known Activations