© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 7965
    Prev
    Next
    INDEX
    Explanations

    references to "plates" in various contexts, indicating a focus on items associated with serving or holding food

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    "plate" or "plates"

    np_acts-logits-general · gemini-2.0-flash

    plate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Bioaccumulative
    -0.57
     հղումներ
    -0.52
    camper
    -0.52
     mochilas
    -0.49
    ++
    -0.49
    Demografie
    -0.48
    niſſe
    -0.47
     Erg
    -0.46
     JMS
    -0.46
    ロウィン
    -0.46
    POSITIVE LOGITS
     plate
    2.38
     Plate
    2.20
    plate
    2.14
     plates
    2.11
    Plate
    2.08
     PLATE
    2.03
     Plates
    1.98
    plates
    1.88
    PLATE
    1.85
    Plates
    1.84
    Activations Density 0.155%

    No Known Activations