© 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. 18-GEMMASCOPE-RES-16K
    11. 259
    Prev
    Next
    INDEX
    Explanations

    code structures and syntax related to C++ programming

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

    C++ code, includes, and namespaces

    np_acts-logits-general · gemini-2.0-flash

    C++ code elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Waray
    -0.73
    verwijspagina
    -0.61
     Signalez
    -0.57
    !*\
    -0.57
    UserScript
    -0.56
    MigrationBuilder
    -0.56
    TintMode
    -0.55
    TRIBUN
    -0.55
     '':
    -0.53
    CloseOperation
    -0.53
    POSITIVE LOGITS
    std
    0.86
     std
    0.83
    ::
    0.82
     nullptr
    0.68
     ::
    0.61
     asio
    0.60
    nullptr
    0.60
    CXX
    0.57
    boost
    0.56
     BOOST
    0.56
    Activations Density 2.039%

    No Known Activations