© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 8951
    Prev
    Next
    INDEX
    Explanations

    expressions of surprise or unexpectedness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hütte
    -0.58
    QUADS
    -0.54
     mục
    -0.54
    bindParam
    -0.54
     Kat
    -0.52
     CURLOPT
    -0.52
    jerc
    -0.52
    tidae
    -0.52
     Fung
    -0.52
     déri
    -0.51
    POSITIVE LOGITS
     Surprise
    1.57
     surprise
    1.56
     surprises
    1.36
     surprised
    1.35
    Surprise
    1.32
    surprise
    1.30
     surpris
    1.29
     surprising
    1.24
     overras
    1.18
    surprised
    1.16
    Activations Density 0.067%

    No Known Activations