© 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. 7-GEMMASCOPE-RES-16K
    11. 1641
    Prev
    Next
    INDEX
    Explanations

    instances of surprise and unexpected outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     al
    -0.54
    QUADS
    -0.53
     T
    -0.51
     I
    -0.50
     san
    -0.50
    QtCore
    -0.49
     E
    -0.49
     unto
    -0.49
     AL
    -0.49
     onto
    -0.48
    POSITIVE LOGITS
     surprise
    1.97
     Surprise
    1.85
     surprised
    1.84
     surprises
    1.68
    Surprise
    1.66
     surpris
    1.63
    surprise
    1.63
    surprised
    1.61
     surprising
    1.58
     overras
    1.49
    Activations Density 0.075%

    No Known Activations