© 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. 20-GEMMASCOPE-RES-16K
    6. 15362
    Prev
    Next
    INDEX
    Explanations

    function calls and system operations related to file handling and I/O in programming

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

    File descriptors in code snippets

    np_acts-logits-general · gemini-2.0-flash

    file descriptors and system calls

    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
    llary
    -0.53
     totalSupply
    -0.50
     thiếu
    -0.49
     Intelli
    -0.45
    zepine
    -0.44
     EconPapers
    -0.44
    NTP
    -0.43
     lacking
    -0.43
     lack
    -0.43
     ECTS
    -0.42
    POSITIVE LOGITS
    Handle
    0.73
     defStyleAttr
    0.71
    findpost
    0.70
    abestanden
    0.69
     fd
    0.68
    FileDescriptor
    0.67
     Handle
    0.65
    Handles
    0.65
    fileID
    0.63
     opened
    0.62
    Activations Density 0.295%

    No Known Activations