© 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. 1350
    Prev
    Next
    INDEX
    Explanations

    instances of back-and-forth motion or actions involving transitions

    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
     Administrativna
    -0.52
    urger
    -0.47
     Shuk
    -0.46
     acidic
    -0.46
     Mercantile
    -0.45
     islanders
    -0.44
     CanadaChoose
    -0.44
     Aimee
    -0.43
    ernet
    -0.43
    ferrer
    -0.43
    POSITIVE LOGITS
    BATH
    0.95
     bath
    0.94
     BATH
    0.93
     Bath
    0.92
    mth
    0.91
    Bath
    0.91
    bath
    0.91
    ETH
    0.90
    meth
    0.88
    Beth
    0.88
    Activations Density 0.695%

    No Known Activations