© 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. 11607
    Prev
    Next
    INDEX
    Explanations

    function definitions and method invocations in programming context

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

    Code involving structs or socket functions

    np_acts-logits-general · gemini-2.0-flash

    Python code constructs

    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
    makeConstraints
    -0.52
     SQLAlchemy
    -0.49
    Obrázky
    -0.48
    ToAction
    -0.45
    Abitanti
    -0.43
    DataSnapshot
    -0.43
     if
    -0.43
    nloa
    -0.43
     leggen
    -0.41
    insee
    -0.40
    POSITIVE LOGITS
     list
    0.71
     len
    0.69
    len
    0.69
     fubject
    0.68
    はじめに
    0.68
     Monfieur
    0.67
     float
    0.67
     None
    0.66
     houſe
    0.65
    InputBorder
    0.65
    Activations Density 0.085%

    No Known Activations