© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 38371
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to image processing and evaluation metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    HPatches Webcam Strecha datasets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     intellectuelle
    -0.39
    OptionsMenu
    -0.38
    UnusedPrivate
    -0.36
     nahilalakip
    -0.36
    úrese
    -0.35
    KindOfClass
    -0.34
    PhysRevD
    -0.34
     cerâmica
    -0.34
    pektor
    -0.33
     écrivain
    -0.33
    POSITIVE LOGITS
    ftagPool
    0.50
    ньому
    0.49
    yelitis
    0.48
     вікісторінку
    0.48
    rinos
    0.47
    liceerd
    0.44
     continúas
    0.44
     heterogeneity
    0.44
     discontinuity
    0.42
     snippetHide
    0.41
    Activations Density 0.058%

    No Known Activations