© 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. 11539
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and symbols, particularly those related to bold and underlined text formatting

    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
     Thurston
    -0.81
     שוליים
    -0.79
    mathbf
    -0.73
     barons
    -0.69
     MDC
    -0.69
    anyuan
    -0.68
    CloseOperation
    -0.68
     Nev
    -0.68
    ymce
    -0.68
     Woodstock
    -0.67
    POSITIVE LOGITS
    boldsymbol
    2.42
     Meridian
    0.70
     prioritise
    0.70
    ราะ
    0.70
     digress
    0.69
    dah
    0.69
    stateParams
    0.68
     Alison
    0.66
     Flach
    0.66
     KIR
    0.65
    Activations Density 0.186%

    No Known Activations