© 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. 20-GEMMASCOPE-RES-16K
    11. 1071
    Prev
    Next
    INDEX
    Explanations

    programming concepts and constructs related to data structures and algorithms

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

    Tokens after "const", "=", or "if"

    np_acts-logits-general · gemini-2.0-flash

    C++ code declarations

    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
    nocache
    -0.71
    MemoryWarning
    -0.65
    createServer
    -0.65
    الإنجليزية
    -0.54
     propOrder
    -0.53
    webElementXpaths
    -0.53
     viewDidLoad
    -0.52
     TRUE
    -0.52
     ModelExpression
    -0.52
    Referencias
    -0.51
    POSITIVE LOGITS
    auto
    1.22
     auto
    1.09
    std
    0.75
     [&
    0.71
    constexpr
    0.71
     Auto
    0.71
     AUTO
    0.69
     std
    0.67
    AUTO
    0.66
    absl
    0.63
    Activations Density 0.288%

    No Known Activations