© 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. 36-GEMMASCOPE-RES-16K
    11. 7347
    Prev
    Next
    INDEX
    Explanations

    references to patient interactions and conditions in a healthcare or medical context, particularly in relation to movement or entry/exit systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     &___
    -0.46
    queryInterface
    -0.45
    DataSetChanged
    -0.42
    msgTypes
    -0.40
    < 
    -0.39
    IntoConstraints
    -0.37
    WithMany
    -0.34
     <>",
    -0.33
    posables
    -0.33
    bkz
    -0.33
    POSITIVE LOGITS
     exit
    2.19
     Exit
    1.99
     exits
    1.88
     exiting
    1.88
     emerge
    1.84
    exit
    1.81
    Exit
    1.80
     emerging
    1.78
     keluar
    1.74
     emerges
    1.73
    Activations Density 0.882%

    No Known Activations