© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105598
    Prev
    Next
    INDEX
    Explanations

    references to class declarations and definitions in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    ьаж
    -0.74
     propOrder
    -0.69
    səhifə
    -0.66
    AndEndTag
    -0.63
     EconPapers
    -0.61
     estekak
    -0.61
    AnchorStyles
    -0.60
     rescate
    -0.59
     onları
    -0.59
     tapaht
    -0.58
    POSITIVE LOGITS
    Class
    0.86
     Class
    0.82
     class
    0.82
    class
    0.79
    EClass
    0.77
     classe
    0.76
     CLASS
    0.76
    CLASS
    0.70
     clazz
    0.70
     classes
    0.69
    Activations Density 0.028%

    No Known Activations