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. 16-GEMMASCOPE-RES-16K
    6. 1555
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming and web development

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

    Paths, URLs, and code snippets

    np_acts-logits-general · gemini-2.0-flash

    developer.apple.com, developer.mozilla.org

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zło
    -0.47
     Pythag
    -0.46
    migrationBuilder
    -0.42
     conmigo
    -0.41
    řeba
    -0.41
     transcur
    -0.40
     상세
    -0.40
    onalds
    -0.40
    apimachinery
    -0.39
    andExpect
    -0.39
    POSITIVE LOGITS
    ]--;
    0.82
    enumi
    0.81
    RegistryLite
    0.80
    PYX
    0.75
     Wikimedijinoj
    0.69
    MessageTagHelper
    0.68
     onOptions
    0.66
    UserScript
    0.64
    Hochspringen
    0.64
    responsible
    0.63
    Activations Density 0.562%

    No Known Activations