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. 22-GEMMASCOPE-RES-16K
    6. 7934
    Prev
    Next
    INDEX
    Explanations

    specific programming and technical terms related to Java and software development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code snippets or Java-related content

    np_acts-logits-general · gemini-2.0-flash

    programming and tort

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EndGlobalSection
    -0.82
    новниш
    -0.68
    Ārējās
    -0.66
    providedIn
    -0.66
    Portail
    -0.65
    Spoljašnje
    -0.59
    aarrggbb
    -0.59
    XmlRootElement
    -0.57
    addCriterion
    -0.56
    createServer
    -0.54
    POSITIVE LOGITS
    GroupLayout
    1.12
    PREFERRED
    1.04
    Alignment
    0.72
     iterable
    0.67
    LayoutStyle
    0.66
    maßen
    0.61
    DEFAULT
    0.61
     ume
    0.60
    PUS
    0.60
     jeste
    0.60
    Activations Density 0.065%

    No Known Activations