© 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. 1850
    Prev
    Next
    INDEX
    Explanations

    instances of the word "of"

    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
    SequentialGroup
    -0.68
    ItemBackground
    -0.54
    Hentet
    -0.53
     ModelExpression
    -0.52
    MLLoader
    -0.51
     alguno
    -0.51
     RoutedEventArgs
    -0.51
     BrowserModule
    -0.51
    Демографія
    -0.50
    GTCX
    -0.50
    POSITIVE LOGITS
     them
    0.68
     these
    0.58
     us
    0.55
     those
    0.51
    them
    0.47
    these
    0.45
    those
    0.40
     yall
    0.38
     swoje
    0.37
     Europe
    0.36
    Activations Density 0.215%

    No Known Activations