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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 8083
    Prev
    Next
    INDEX
    Explanations

    technical programming concepts related to command-line options and parsing

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

    Code, especially related to parsers or arguments

    np_acts-logits-general · gemini-2.0-flash

    command line argument parsers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HideFlags
    -0.53
     Integrals
    -0.52
     Aja
    -0.50
     Jaco
    -0.49
    ونس
    -0.48
    jspx
    -0.47
     Formulas
    -0.47
     Italijani
    -0.47
    IntentFilter
    -0.46
    Xna
    -0.46
    POSITIVE LOGITS
    ArgumentParser
    1.09
     argparse
    0.98
    PARSER
    0.70
     parser
    0.70
    PRNewswire
    0.70
     getopt
    0.67
    Parser
    0.65
    parser
    0.64
    Parsing
    0.64
     parsing
    0.63
    Activations Density 0.099%

    No Known Activations