© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 14650
    Prev
    Next
    INDEX
    Explanations

    references to characters and events involving leadership and authority

    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
     Ny
    -0.36
     pisau
    -0.34
    Ny
    -0.33
    AndEndTag
    -0.32
     bouw
    -0.32
     Dow
    -0.31
    sproz
    -0.31
     Holloway
    -0.31
     kości
    -0.31
     Thom
    -0.30
    POSITIVE LOGITS
     Vegeta
    0.90
     Goku
    0.88
     vegeta
    0.82
    Vegeta
    0.82
     Gohan
    0.81
     goku
    0.79
     Trunks
    0.77
    Goku
    0.77
     Saiyan
    0.76
     Veget
    0.66
    Activations Density 0.400%

    No Known Activations