© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 12275
    Prev
    Next
    INDEX
    Explanations

    terms related to citizenship and legal status within a political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     moniker
    -0.91
     showcasing
    -0.89
     proactively
    -0.87
     leveraging
    -0.84
     incentiv
    -0.83
     prioritizing
    -0.82
     showcased
    -0.81
     timeframe
    -0.78
     blurry
    -0.77
     aligns
    -0.76
    POSITIVE LOGITS
     skall
    0.42
     muß
    0.39
     läßt
    0.37
     gewisser
    0.37
     rôles
    0.36
     מן
    0.36
     fotográfica
    0.36
     vrou
    0.36
     mußten
    0.35
     czarna
    0.35
    Activations Density 2.129%

    No Known Activations