© 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. 3-GEMMASCOPE-RES-16K
    11. 13213
    Prev
    Next
    INDEX
    Explanations

    instances of the word "extra."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 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
    SourceChecksum
    -0.80
    TypedDataSet
    -0.75
     végétale
    -0.75
     acidosis
    -0.70
     Barbosa
    -0.69
     initComponents
    -0.69
     cardiaque
    -0.69
    iseaux
    -0.68
    jsxFileName
    -0.67
     Biosciences
    -0.66
    POSITIVE LOGITS
     extra
    3.73
     Extra
    3.39
    extra
    3.28
    Extra
    3.24
     EXTRA
    3.18
    EXTRA
    2.78
     ekstra
    2.62
     extras
    2.37
     Extras
    2.29
    extras
    2.17
    Activations Density 0.086%

    No Known Activations