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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 12-GEMMASCOPE-RES-16K
    6. 2799
    Prev
    Next
    INDEX
    Explanations

    HTML tags and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -0.57
     ویکی‌پدیای
    -0.56
    日閲覧
    -0.51
    SPATH
    -0.50
     виправивши
    -0.49
    readAs
    -0.47
    Tras
    -0.47
     beschik
    -0.47
    webElementGuid
    -0.47
    :\/\/
    -0.47
    POSITIVE LOGITS
     title
    1.01
     标题
    0.87
     titulo
    0.86
     getTitle
    0.85
    title
    0.83
    TITLE
    0.79
    setTitle
    0.77
     Title
    0.77
     TITLE
    0.77
    titulo
    0.75
    Activations Density 0.110%

    No Known Activations