Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 9993
    Prev
    Next
    INDEX
    Explanations

    references to historical or legal codes related to accidents and employment

    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
     ExecuteAsync
    -0.72
    Erreferentziak
    -0.61
     архивлан
    -0.61
    resz
    -0.60
    nloa
    -0.58
    Datuak
    -0.56
    TAWA
    -0.56
    ContentAsync
    -0.53
     referrerpolicy
    -0.52
     bewer
    -0.51
    POSITIVE LOGITS
     Virginia
    1.34
    Virginia
    1.18
     VIRGINIA
    1.13
     virginia
    1.06
     Charlottesville
    0.97
     Roanoke
    0.96
     Virginie
    0.89
     UVA
    0.87
     VA
    0.87
     Va
    0.86
    Activations Density 0.179%

    No Known Activations