© 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-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 12899
    Prev
    Next
    INDEX
    Explanations

    references to representatives and legislative roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.74
    simpleType
    -0.74
    tableFuture
    -0.74
     Ral
    -0.72
     Viter
    -0.69
    clusal
    -0.69
    prefixer
    -0.69
    extAlignment
    -0.67
     Dolom
    -0.67
    infeld
    -0.67
    POSITIVE LOGITS
     Rep
    2.38
    Rep
    2.23
     rep
    2.20
    rep
    2.09
     Reps
    1.98
     reps
    1.85
     Representative
    1.79
    Reps
    1.78
    reps
    1.63
    Representative
    1.61
    Activations Density 0.165%

    No Known Activations