© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 16161
    Prev
    Next
    INDEX
    Explanations

    requests for information or assistance

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     albeit
    -0.55
    albeit
    -0.54
    tvguidetime
    -0.50
     whatnot
    -0.49
     poichè
    -0.46
    とはいえ
    -0.41
     seemingly
    -0.41
     IIRC
    -0.38
     amongst
    -0.38
     oftentimes
    -0.38
    POSITIVE LOGITS
     Attractive
    0.57
     obey
    0.57
     Porque
    0.56
     contain
    0.55
     calculate
    0.54
     Frist
    0.54
     irritate
    0.54
     protect
    0.53
     combine
    0.52
     apply
    0.52
    Activations Density 0.356%

    No Known Activations