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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 14198
    Prev
    Next
    INDEX
    Explanations

    sequences of brackets or delimiters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Duch
    -0.71
    stech
    -0.69
    <i>
    -0.68
    Française
    -0.67
    beiros
    -0.66
    Dalton
    -0.65
     marquer
    -0.64
    )$}
    -0.64
    utura
    -0.64
    fonte
    -0.64
    POSITIVE LOGITS
    ][
    1.42
    ()][
    1.04
    )][
    0.99
    [][
    0.92
     ][
    0.92
    webElementXpaths
    0.78
    kháu
    0.75
    ]][
    0.75
    )(
    0.73
    gorm
    0.70
    Activations Density 0.222%

    No Known Activations