© 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-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 16271
    Prev
    Next
    INDEX
    Explanations

    phrases indicating choice or options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     selected
    -0.86
     Selected
    -0.84
    Selected
    -0.78
    selected
    -0.77
     SELECTED
    -0.72
     selezion
    -0.65
     sélectionné
    -0.63
     Selecting
    -0.55
     sélectionnés
    -0.54
     seleccionadas
    -0.54
    POSITIVE LOGITS
     choice
    2.05
    choice
    1.82
     Choice
    1.73
     CHOICE
    1.66
    Choice
    1.63
     choix
    1.53
    CHOICE
    1.48
     cho
    1.46
     choices
    1.43
     CHO
    1.35
    Activations Density 0.329%

    No Known Activations