© 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. 15-GEMMASCOPE-RES-16K
    11. 5988
    Prev
    Next
    INDEX
    Explanations

    medical terms related to severe diseases and their associated morbidities and mortalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sna
    -0.43
     regulares
    -0.41
    MockBean
    -0.40
     regular
    -0.39
    EndProject
    -0.39
     maestra
    -0.38
     sentada
    -0.37
     Moseley
    -0.37
     qued
    -0.37
    regular
    -0.36
    POSITIVE LOGITS
    StoryboardSegue
    0.55
     utafitiHapana
    0.53
     remor
    0.49
     سكانية
    0.48
     fatality
    0.47
     Efq
    0.47
    TagMode
    0.46
     autorytatywna
    0.45
     fatal
    0.45
     mortality
    0.44
    Activations Density 0.771%

    No Known Activations