© 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. 3-GEMMASCOPE-RES-16K
    11. 7406
    Prev
    Next
    INDEX
    Explanations

    references to political leadership or the title of a governor

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cố
    -0.38
     مُعرِّف
    -0.35
     zesta
    -0.34
     sẻ
    -0.34
    isure
    -0.34
     religiosa
    -0.33
     către
    -0.33
     poire
    -0.32
     المسلمين
    -0.31
     chileno
    -0.31
    POSITIVE LOGITS
     governor
    1.92
     Governor
    1.81
    Governor
    1.78
    governor
    1.66
     GOVERNOR
    1.63
     province
    1.59
     gouverneur
    1.43
     governors
    1.38
     governorship
    1.37
     Province
    1.32
    Activations Density 0.053%

    No Known Activations