© 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. 0-GEMMASCOPE-RES-16K
    6. 1836
    Prev
    Next
    INDEX
    Explanations

    instances of the word "cancel" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     appunt
    -0.61
     exportación
    -0.59
     metodología
    -0.57
     acompañado
    -0.56
     reuniones
    -0.56
     cuenca
    -0.56
     aguja
    -0.56
     fotográfica
    -0.55
     ympä
    -0.55
     pierna
    -0.54
    POSITIVE LOGITS
     cancel
    0.77
     Cancel
    0.73
     refer
    0.73
    cancel
    0.64
    \{\\
    0.59
    sizeCache
    0.59
    Cancel
    0.57
     autorytatywna
    0.56
     المعيارى
    0.55
     Infórmanos
    0.55
    Activations Density 0.354%

    No Known Activations