© 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. 39-GEMMASCOPE-RES-16K
    11. 4386
    Prev
    Next
    INDEX
    Explanations

    instances of the word "but" or variations thereof, indicating a contrast in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Though
    -0.59
    Though
    -0.57
     ویکی‌پدی
    -0.50
     and
    -0.48
     THOUGH
    -0.47
    though
    -0.45
    able
    -0.41
     sice
    -0.40
    oredCriteria
    -0.39
    Aunque
    -0.39
    POSITIVE LOGITS
     then
    1.07
     hey
    1.00
    terscotch
    0.99
    termilk
    0.96
     alas
    0.89
    chery
    0.86
     also
    0.84
    chers
    0.82
     nevertheless
    0.80
    ternut
    0.80
    Activations Density 0.153%

    No Known Activations