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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 30-GEMMASCOPE-RES-16K
    6. 10883
    Prev
    Next
    INDEX
    Explanations

    components and their associated code structures in programming syntax

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

    Keywords in Javascript/Typescript and code imports

    np_acts-logits-general · gemini-2.0-flash

    code imports and declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.77
    Hentet
    -0.72
    UrlResolution
    -0.67
     مرئيه
    -0.65
     EconPapers
    -0.65
    +#+#
    -0.64
     disambiguazione
    -0.64
    ➋
    -0.63
    
    -0.63
    OGND
    -0.61
    POSITIVE LOGITS
    const
    0.47
    export
    0.44
    namespace
    0.39
    import
    0.37
     const
    0.36
     export
    0.34
    ječ
    0.30
    ąp
    0.28
     nahilalakip
    0.28
    class
    0.28
    Activations Density 0.089%

    No Known Activations