© 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. 6346
    Prev
    Next
    INDEX
    Explanations

    components related to mechanical engineering and heating systems

    oai_token-act-pair · gpt-4o-miniTriggered 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
     printing
    -1.57
     print
    -1.53
     Printing
    -1.43
     printer
    -1.38
     printers
    -1.38
    printing
    -1.38
    Printing
    -1.36
     prints
    -1.34
    print
    -1.34
     printed
    -1.33
    POSITIVE LOGITS
    кобрита
    0.53
     سكانية
    0.53
    PAIGN
    0.53
     OnTriggerEnter
    0.51
    waite
    0.48
    躇
    0.48
    Ecotoxicity
    0.47
     Weak
    0.47
    acos
    0.46
    RowCount
    0.46
    Activations Density 0.214%

    No Known Activations