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. 20-GEMMASCOPE-RES-16K
    6. 12412
    Prev
    Next
    INDEX
    Explanations

    references to education and educational institutions

    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
    webElementXpaths
    -0.64
    othelioma
    -0.60
    Legături
    -0.57
    WriteTagHelper
    -0.56
    DockStyle
    -0.54
    mortem
    -0.54
    SourceChecksum
    -0.54
    ˈ
    -0.53
    WebElementEntity
    -0.52
    VersionUID
    -0.52
    POSITIVE LOGITS
     institutions
    0.68
     Italijanski
    0.65
     institution
    0.63
     Institutions
    0.60
    institution
    0.59
     referenties
    0.59
    ally
    0.59
     Institution
    0.58
     riguardo
    0.56
    sprogramm
    0.56
    Activations Density 0.037%

    No Known Activations