© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 103537
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "surprise" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     affinch
    -0.49
     dentaire
    -0.41
     kepem
    -0.39
     hendes
    -0.38
     trabal
    -0.37
     bruge
    -0.36
     brugt
    -0.36
     columnas
    -0.36
     chacune
    -0.36
    før
    -0.35
    POSITIVE LOGITS
     Surprise
    1.25
     surprise
    1.23
    Surprise
    1.19
    surprise
    1.16
     surprises
    1.06
     surpris
    0.97
     surprised
    0.95
     sorpresa
    0.90
    surprised
    0.86
    юрпри
    0.85
    Activations Density 0.010%

    No Known Activations