© 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. 10599
    Prev
    Next
    INDEX
    Explanations

    instances of code structure related to thread management and array handling in programming

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

    Followed by ".length" or "Arrays."

    np_acts-logits-general · gemini-2.0-flash

    java.util.Arrays methods

    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
     <=",
    -0.47
    List
    -0.47
    list
    -0.45
     Monats
    -0.44
    gonic
    -0.44
     al
    -0.43
     тре
    -0.42
    LIST
    -0.42
    map
    -0.41
     List
    -0.41
    POSITIVE LOGITS
    assertArray
    0.74
     مرئيه
    0.69
    IntArray
    0.67
    arrayOf
    0.66
    Arrays
    0.65
     raiſ
    0.65
    fjspx
    0.65
     arrayOf
    0.64
     通販
    0.64
    出版年
    0.64
    Activations Density 0.099%

    No Known Activations