© 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-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 4466
    Prev
    Next
    INDEX
    Explanations

    programming constructs and identifiers related to Java and event-handler functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     chi̍t
    -0.43
     would
    -0.36
    __(/*!
    -0.34
     fapt
    -0.31
    卻
    -0.30
     geloof
    -0.29
    Gweler
    -0.29
     zouden
    -0.29
    évaluateur
    -0.29
    AccessorTable
    -0.28
    POSITIVE LOGITS
    impl
    0.71
    ereq
    0.57
    idance
    0.56
     ſelbſt
    0.56
     zwiſchen
    0.55
    Abstract
    0.55
     implementations
    0.54
     basics
    0.53
     bases
    0.53
    ꪹ
    0.53
    Activations Density 0.343%

    No Known Activations