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. 6478
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial assistance and credit options for individuals with poor credit histories

    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
     Toward
    -0.55
    toward
    -0.48
     menudo
    -0.48
    গু
    -0.48
    stacles
    -0.46
    rogly
    -0.46
    leqq
    -0.46
    meid
    -0.43
    EndGlobalSection
    -0.43
    Toward
    -0.43
    POSITIVE LOGITS
     availed
    0.84
     severally
    0.78
     commonest
    0.78
     hence
    0.77
     adverts
    0.75
     spoilt
    0.74
     ویکی‌پدیای
    0.72
     Programmes
    0.71
     advert
    0.71
     learnt
    0.69
    Activations Density 0.266%

    No Known Activations