© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 381
    Prev
    Next
    INDEX
    Explanations

    return statements in code

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

    Keywords before boolean "false" or "void"

    np_acts-logits-general · gemini-2.0-flash

    programming return statements

    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
    awtextra
    -0.70
     AssemblyCompany
    -0.62
     }{@
    -0.60
     发表于
    -0.58
    ConstraintMaker
    -0.58
    ViewImports
    -0.58
    URLException
    -0.57
     textStatus
    -0.55
    NameInMap
    -0.55
     IconData
    -0.53
    POSITIVE LOGITS
    void
    0.75
     void
    0.74
    VOID
    0.72
    tvguidetime
    0.67
     false
    0.64
    Void
    0.60
    didSet
    0.56
     False
    0.55
     Void
    0.55
    ]='\
    0.54
    Activations Density 0.046%

    No Known Activations