© 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. 33-GEMMASCOPE-RES-16K
    11. 12742
    Prev
    Next
    INDEX
    Explanations

    expressions of deference and respect towards authority figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wikimedijinoj
    -0.40
     sassy
    -0.36
     defiance
    -0.35
    terape
    -0.35
    makeConstraints
    -0.35
     defiant
    -0.34
     biographer
    -0.34
     rogue
    -0.33
    お待ちしております
    -0.33
     dodgy
    -0.33
    POSITIVE LOGITS
     Honorable
    1.09
     honorable
    1.02
     Honourable
    1.02
     honourable
    0.97
     Excell
    0.96
    Excell
    0.93
    Honorable
    0.91
     Hon
    0.91
     honored
    0.89
     Excellency
    0.89
    Activations Density 0.276%

    No Known Activations