© 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. 12-GEMMASCOPE-RES-16K
    11. 2335
    Prev
    Next
    INDEX
    Explanations

    references to grid structures or grid layouts

    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
    CloseOperation
    -0.48
    ceq
    -0.39
     ActionListener
    -0.39
     Cesar
    -0.38
    ="@+
    -0.38
    ActionPerformed
    -0.38
    uA
    -0.38
    حياته
    -0.37
    Cesar
    -0.37
    (!)
    -0.36
    POSITIVE LOGITS
     grid
    2.08
    grid
    1.88
     Grid
    1.86
    Grid
    1.75
     GRID
    1.72
     grids
    1.65
    GRID
    1.61
    grids
    1.33
    isGrid
    1.03
    GridView
    1.01
    Activations Density 0.158%

    No Known Activations