© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 13996
    Prev
    Next
    INDEX
    Explanations

    expressions of surprise or shock

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     plumas
    -0.37
    ฬ
    -0.35
     prohibido
    -0.35
     GLFW
    -0.35
     besch
    -0.34
     skrive
    -0.34
     brasileño
    -0.34
     delgado
    -0.32
     jurídico
    -0.32
     aulas
    -0.32
    POSITIVE LOGITS
     surprise
    1.64
     surprises
    1.54
     surprised
    1.48
    Surprise
    1.46
     Surprise
    1.45
    surprise
    1.43
     unexpected
    1.38
     sorpresa
    1.37
     surprising
    1.36
     Überras
    1.31
    Activations Density 0.196%

    No Known Activations