© 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. 1-GEMMASCOPE-RES-16K
    11. 5048
    Prev
    Next
    INDEX
    Explanations

    references to nominations and nominees in political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     zoude
    -0.53
    /**
    -0.53
    //
    -0.45
     Mileage
    -0.44
     חיצוניים
    -0.44
     okuyayım
    -0.44
    ashimi
    -0.43
     zijne
    -0.42
    famili
    -0.42
     gracilis
    -0.42
    POSITIVE LOGITS
     Nom
    1.16
    Nom
    1.13
     nom
    1.09
    nom
    0.98
     nominee
    0.97
     NOM
    0.94
     nomination
    0.91
     nominate
    0.90
     nominated
    0.89
     Nomination
    0.89
    Activations Density 0.472%

    No Known Activations