© 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
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 10306
    Prev
    Next
    INDEX
    Explanations

    terms and structures related to bounding boxes in image processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    webElementXpaths
    -0.54
     culturelle
    -0.48
     ferons
    -0.46
    хьтан
    -0.46
     muerta
    -0.44
     arrep
    -0.43
    ſelves
    -0.43
     littéraire
    -0.42
     partida
    -0.41
     dimensión
    -0.41
    POSITIVE LOGITS
     COC
    0.59
     coco
    0.54
     boxes
    0.54
     Dete
    0.54
     Io
    0.53
     detections
    0.52
     dete
    0.52
     Bound
    0.50
     Boxes
    0.50
     Detection
    0.48
    Activations Density 0.188%

    No Known Activations