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. 13875
    Prev
    Next
    INDEX
    Explanations

    terms associated with rugby and its regional references in Great Britain

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows "New" or "rugby"

    np_acts-logits-general · gemini-2.0-flash

    Papua New Guinea rugby

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    őbb
    -0.48
    ereq
    -0.47
    tadır
    -0.46
    opcao
    -0.46
    िका
    -0.45
    ragamo
    -0.44
     plancher
    -0.43
     dés
    -0.43
     yan
    -0.43
     dj
    -0.43
    POSITIVE LOGITS
    tvguidetime
    0.79
     chi̍t
    0.67
     Paglinawan
    0.64
    HasAnnotation
    0.64
     Papua
    0.62
     Mores
    0.62
     متعلقه
    0.62
    WaitGroup
    0.61
    verwijspagina
    0.61
    iNdEx
    0.59
    Activations Density 0.070%

    No Known Activations