© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 10320
    Prev
    Next
    INDEX
    Explanations

    references to plates and their variations in context

    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
     Sheet
    -0.74
     sheet
    -0.70
     SHEET
    -0.67
    Sheet
    -0.66
    heet
    -0.62
    heets
    -0.61
     sheets
    -0.57
    sheet
    -0.55
    Sheets
    -0.52
     Sheets
    -0.52
    POSITIVE LOGITS
     plate
    1.91
     Plate
    1.68
    plate
    1.63
     plates
    1.60
    Plate
    1.56
     PLATE
    1.51
     Plates
    1.45
    plates
    1.39
    Plates
    1.33
    PLATE
    1.31
    Activations Density 0.099%

    No Known Activations