© 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. 334
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and keywords

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

    C/C++ integer variable declarations

    np_acts-logits-general · gemini-2.0-flash

    integer declaration or usage

    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
    播
    -0.53
     loose
    -0.51
     Bonif
    -0.48
     Woodward
    -0.47
    nene
    -0.45
    lader
    -0.44
    ADER
    -0.44
    Didier
    -0.44
    hpp
    -0.44
     fashion
    -0.43
    POSITIVE LOGITS
    int
    1.96
     int
    1.85
    INT
    1.30
    Int
    1.21
     INT
    1.18
     Int
    1.18
    setInt
    1.09
     ints
    1.05
    ints
    1.03
    ToInt
    1.02
    Activations Density 0.068%

    No Known Activations