© 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-2-2B
    7. MLP Out - 16k
    9. 19-GEMMASCOPE-MLP-16K
    11. 6162
    Prev
    Next
    INDEX
    Explanations

    concepts of damage and the potential for repair

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_19/width_16k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_mlp_out
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    zerű
    -0.57
    mybatisplus
    -0.55
     Griechen
    -0.54
    licitations
    -0.51
    datatables
    -0.51
    boda
    -0.49
     CYTHON
    -0.48
    nestjs
    -0.48
     griech
    -0.47
    KommentareTeilen
    -0.47
    POSITIVE LOGITS
     repair
    1.11
    repair
    1.08
     repaired
    1.02
     repairing
    1.00
     repairs
    0.99
     Repair
    0.96
     REPAIR
    0.95
     reconstruction
    0.92
     rebuild
    0.91
     restoration
    0.91
    Activations Density 0.364%

    No Known Activations