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

    Neuronpedia

    Jacobian LensNEW
    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. 20-GEMMASCOPE-RES-16K
    11. 8548
    Prev
    Next
    INDEX
    Explanations

    syntax and structure related to programming, specifically in defining functions and data types

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

    Data types and related keywords

    np_acts-logits-general · gemini-2.0-flash

    type annotations and function signatures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #
    -0.62
    ViewFeatures
    -0.60
    ніципалі
    -0.57
    ReferenceEquals
    -0.56
     <>",
    -0.56
     Kerk
    -0.55
     препратки
    -0.55
     yii
    -0.54
    ulir
    -0.53
     tslint
    -0.52
    POSITIVE LOGITS
     Int
    0.79
    Int
    0.77
     Any
    0.76
     String
    0.65
    Any
    0.65
     Double
    0.55
    Bool
    0.55
    String
    0.54
    Double
    0.53
    SuspendLayout
    0.53
    Activations Density 0.154%

    No Known Activations