© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 15474
    Prev
    Next
    INDEX
    Explanations

    specific programming syntax or constructs in code

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

    Code related to integer types (int, Int,INT)

    np_acts-logits-general · gemini-2.0-flash

    integer type declaration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ecotoxicity
    -0.56
    beyond
    -0.52
    createServer
    -0.49
     Beyond
    -0.49
    ായ
    -0.49
    WireFormatLite
    -0.49
     besides
    -0.48
    mole
    -0.48
     phase
    -0.48
     Than
    -0.48
    POSITIVE LOGITS
     int
    2.54
    int
    2.52
    Int
    1.46
     Int
    1.42
    INT
    1.25
     ints
    1.15
     INT
    1.14
    setInt
    1.04
    intar
    1.03
    ints
    1.01
    Activations Density 0.088%

    No Known Activations