© 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. 3587
    Prev
    Next
    INDEX
    Explanations

    C++ programming constructs, such as include directives and template definitions

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

    C++ code and related keywords

    np_acts-logits-general · gemini-2.0-flash

    C++ code structure and inclusion

    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
    UIControlState
    -0.79
    ędziesz
    -0.72
    rungsseite
    -0.72
     ***!
    -0.66
     محفوظة
    -0.61
    Tembelea
    -0.61
     -->>
    -0.61
     Signalez
    -0.59
    DockStyle
    -0.58
    AutoresizingMask
    -0.58
    POSITIVE LOGITS
    int
    0.84
     int
    0.71
     void
    0.66
    using
    0.65
    void
    0.63
    Concurrency
    0.59
    bool
    0.58
    typedef
    0.56
     bool
    0.55
    #
    0.53
    Activations Density 0.145%

    No Known Activations