© 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. 37-GEMMASCOPE-RES-16K
    11. 9107
    Prev
    Next
    INDEX
    Explanations

    destructive actions and their impacts on people and society

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     potrzeby
    -0.38
     needs
    -0.36
    bedarf
    -0.35
    SerializeField
    -0.35
     probl
    -0.33
    Становништво
    -0.33
     HttpNotFound
    -0.32
     problem
    -0.32
    PROBLE
    -0.31
     problém
    -0.31
    POSITIVE LOGITS
     innocent
    1.31
    innocent
    1.30
    innoc
    1.09
     inocente
    1.05
     innocence
    1.03
     unsuspecting
    1.00
     innoc
    0.98
    Innoc
    0.94
     reputations
    0.93
     livelihoods
    0.92
    Activations Density 0.985%

    No Known Activations