© 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. 1517
    Prev
    Next
    INDEX
    Explanations

    HTML and CSS attributes related to display properties and conditions

    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
    Према
    -0.52
     transfieras
    -0.40
     OMITBAD
    -0.38
     Meksiku
    -0.37
    识
    -0.34
     <>",
    -0.34
     sâu
    -0.33
    protoimpl
    -0.32
     PeEnEo
    -0.31
     itinéraires
    -0.31
    POSITIVE LOGITS
     inline
    1.01
     flex
    0.89
    inline
    0.87
    flex
    0.82
     Inline
    0.71
    Inline
    0.68
    INLINE
    0.63
     absolute
    0.63
     relative
    0.62
     Flex
    0.61
    Activations Density 0.216%

    No Known Activations