© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 62723
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    حياته
    -1.76
    حياتها
    -1.33
    脚注の使い方
    -1.20
     насељу
    -1.20
     lenker
    -1.19
     autorytatywna
    -0.84
     مرئيه
    -0.82
     للمعارف
    -0.82
    GEBURTSDATUM
    -0.82
     CreateTagHelper
    -0.75
    POSITIVE LOGITS
    ClientSize
    0.95
    Metadata
    0.74
    Bodies
    0.62
    dataflow
    0.62
    otus
    0.46
     Metadata
    0.36
     DbSet
    0.34
     Bodies
    0.33
    metadata
    0.32
     arşivlendi
    0.30
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.