© 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. 3-GEMMASCOPE-RES-16K
    11. 8324
    Prev
    Next
    INDEX
    Explanations

    references to grid structures and configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    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
    -0.55
    postsleuth
    -0.40
     ActionListener
    -0.40
     neurop
    -0.38
     @"/
    -0.37
    Externé
    -0.37
    errated
    -0.36
     AssemblyCompany
    -0.36
    got
    -0.35
     premier
    -0.35
    POSITIVE LOGITS
     grid
    2.06
    grid
    1.90
     Grid
    1.81
    Grid
    1.68
     grids
    1.64
     GRID
    1.51
    GRID
    1.42
    grids
    1.25
     gri
    1.04
     grille
    0.98
    Activations Density 0.084%

    No Known Activations