Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15734
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and constructs used for handling input/output and conditionals

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

    Code-related tokens

    np_acts-logits-general · gemini-2.0-flash

    code structure and programming 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
    RTEE
    -0.83
    Vidite
    -0.72
    stateParams
    -0.72
     незавершена
    -0.68
     }{@
    -0.67
    WireFormatLite
    -0.66
    amaño
    -0.66
    XmlAccessType
    -0.66
     Numerology
    -0.65
    CppCodeGen
    -0.65
    POSITIVE LOGITS
    SupportActionBar
    0.56
    ++]
    0.56
    ++);
    0.53
     متعلقه
    0.50
    ++]=
    0.50
    ыгана
    0.47
    tuur
    0.47
    {}\
    0.46
     memoized
    0.46
    下载附件
    0.46
    Activations Density 0.182%

    No Known Activations