© 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. 25-GEMMASCOPE-RES-16K
    11. 15298
    Prev
    Next
    INDEX
    Explanations

    code elements related to programming and database queries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     high
    -0.34
     right
    -0.34
     the
    -0.34
     well
    -0.34
     working
    -0.34
     quality
    -0.34
     clean
    -0.34
     building
    -0.34
     full
    -0.34
     being
    -0.34
    POSITIVE LOGITS
     varandra
    0.85
     enfans
    0.79
     avoient
    0.78
     stället
    0.77
     feroit
    0.76
     étoient
    0.73
     auroit
    0.73
     prêtres
    0.72
     prisonniers
    0.72
     dieux
    0.71
    Activations Density 51.369%

    No Known Activations