© 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. 37-GEMMASCOPE-RES-16K
    11. 7148
    Prev
    Next
    INDEX
    Explanations

    technical terms or parameters related to configuration settings

    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
    newtheorem
    -0.32
    Won
    -0.29
     Won
    -0.29
    沙
    -0.28
    uction
    -0.28
     won
    -0.28
     APPLICABLE
    -0.28
    LIBR
    -0.27
    GNUC
    -0.27
     wont
    -0.27
    POSITIVE LOGITS
    HomeAsUpEnabled
    0.65
    Билгалдахарш
    0.64
    :✨
    0.60
                                  
    0.59
     témoig
    0.56
     estekak
    0.56
     mergeFrom
    0.54
                                 
    0.54
     vooz
    0.54
    rénées
    0.52
    Activations Density 0.278%

    No Known Activations