© 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 - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 15362
    Prev
    Next
    INDEX
    Explanations

    references to the JavaX library in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StructEnd
    -0.92
     Klon
    -0.77
    KommentareTeilen
    -0.70
     riuscito
    -0.67
     comet
    -0.65
     tails
    -0.65
    Demografie
    -0.63
     chutes
    -0.63
    VideoCapture
    -0.63
     Torna
    -0.63
    POSITIVE LOGITS
     javax
    3.15
    javax
    1.49
     initWithFrame
    0.70
     חיצוניים
    0.67
    ']?>
    0.64
    lognese
    0.63
    burgo
    0.62
    ภา
    0.62
    ,‎
    0.61
    bex
    0.61
    Activations Density 0.014%

    No Known Activations