© 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. 5636
    Prev
    Next
    INDEX
    Explanations

    occurrences of legal terms and concepts related to authority and obligations

    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
     Those
    -0.52
     onPage
    -0.48
     That
    -0.48
     Isso
    -0.47
     This
    -0.47
    Cyfarwyddwr
    -0.46
    Those
    -0.45
     THOSE
    -0.44
    它们的
    -0.43
     Esa
    -0.43
    POSITIVE LOGITS
    تقاوى
    0.53
     cherchés
    0.51
    MemoryWarning
    0.48
     للمعارف
    0.45
    该
    0.45
    該
    0.45
     klubben
    0.44
    IsMutable
    0.44
    toMatchSnapshot
    0.43
    SourceChecksum
    0.43
    Activations Density 0.545%

    No Known Activations