© 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. 36-GEMMASCOPE-RES-16K
    11. 12051
    Prev
    Next
    INDEX
    Explanations

    references to political or economic topics discussing change or transitions in systems

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    SourceChecksum
    -0.35
    BagConstraints
    -0.29
    kungan
    -0.29
    الحياه
    -0.28
    kawi
    -0.28
     पढ़ें
    -0.27
    icordia
    -0.26
     cherchés
    -0.26
     balles
    -0.26
     pää
    -0.25
    POSITIVE LOGITS
     surge
    1.73
     boom
    1.57
     wave
    1.45
     resurgence
    1.44
     explosion
    1.42
     rise
    1.33
     spike
    1.31
     influx
    1.31
     deluge
    1.27
     spurt
    1.27
    Activations Density 0.630%

    No Known Activations