© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 3718
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming constructs related to system or file handling in various programming languages

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

    Code-related keywords

    np_acts-logits-general · gemini-2.0-flash

    import, include, define code

    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
    __["
    -0.70
    AddHtmlAttribute
    -0.68
    AddTagHelper
    -0.66
    Personensuche
    -0.66
     OFDb
    -0.66
    Jeografia
    -0.65
    IndentedString
    -0.65
    sizeCache
    -0.64
     ModelExpression
    -0.64
    OGND
    -0.64
    POSITIVE LOGITS
    ^(@)
    1.03
    >\<^
    0.71
     Wikispecies
    0.66
    intenance
    0.64
    ientras
    0.63
     NDEBUG
    0.61
    etheless
    0.61
    BRUARY
    0.60
    ividual
    0.60
    ergies
    0.59
    Activations Density 0.234%

    No Known Activations