© 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 EvalsExportsinterp-engineNEWAPI 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. 6105
    Prev
    Next
    INDEX
    Explanations

    references to specific video games and proteins associated with cancer research

    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
     viewDidLoad
    -0.46
     LV
    -0.43
     Fus
    -0.39
     AppBar
    -0.38
     DV
    -0.38
     PV
    -0.38
     Nen
    -0.37
    mapStateToProps
    -0.36
     Bolton
    -0.36
     Trapp
    -0.35
    POSITIVE LOGITS
     Sonic
    1.08
    Sonic
    1.01
     hedgehog
    0.83
     Knuckles
    0.83
    ソニック
    0.81
     sonic
    0.80
     Hedgehog
    0.79
    sonic
    0.78
     Tails
    0.75
    🦔
    0.71
    Activations Density 0.200%

    No Known Activations