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. 10062
    Prev
    Next
    INDEX
    Explanations

    events or actions related to sports, particularly baseball

    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
    ContentAsync
    -0.72
    RefNanny
    -0.62
     tongs
    -0.61
    ReusableCell
    -0.60
    sizeCache
    -0.59
     linkovi
    -0.57
     snippetHide
    -0.57
    setVerticalGroup
    -0.54
    iaomi
    -0.52
    ViewImports
    -0.52
    POSITIVE LOGITS
     singles
    0.67
    sing
    0.62
    Drive
    0.55
     strings
    0.55
     sing
    0.54
    äfts
    0.54
     hit
    0.54
     single
    0.53
     drive
    0.53
     Drive
    0.53
    Activations Density 0.137%

    No Known Activations