© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 14478
    Prev
    Next
    INDEX
    Explanations

    phrases relating to decision-making and legal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -0.52
     الرياضيه
    -0.52
    numerusform
    -0.49
    Insee
    -0.48
    Filmografie
    -0.48
     Paglinawan
    -0.47
    NewUrlParser
    -0.47
    ThroughAttribute
    -0.47
     pinulongan
    -0.47
    ualaikum
    -0.46
    POSITIVE LOGITS
     depends
    0.93
     dependent
    0.80
     subjective
    0.79
     depende
    0.78
     Depends
    0.77
     depend
    0.77
    Depends
    0.76
     dépend
    0.75
    depends
    0.73
     зависит
    0.71
    Activations Density 0.480%

    No Known Activations