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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 2433
    Prev
    Next
    INDEX
    Explanations

    code related to file input/output operations in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    verwijspagina
    -0.73
     дописавши
    -0.71
     '{@
    -0.66
     EconPapers
    -0.64
     تضيفلها
    -0.58
    Искәрмәләр
    -0.57
    enschappelijke
    -0.57
     Chwiliwch
    -0.57
     estekak
    -0.56
    ///</
    -0.56
    POSITIVE LOGITS
    stdout
    0.66
    HAEL
    0.61
     IOError
    0.60
     stdout
    0.60
     getchar
    0.59
    stderr
    0.56
     stderr
    0.55
     PrintWriter
    0.55
    fflush
    0.54
     Liber
    0.53
    Activations Density 0.013%

    No Known Activations