© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 14516
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals and entities involved in legal or political contexts

    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
    ~/
    -0.43
    bamos
    -0.33
     amigas
    -0.33
     &___
    -0.33
    httphttps
    -0.31
     lizenzfreie
    -0.31
    ⊷
    -0.31
     nek
    -0.30
     muchas
    -0.30
     specchio
    -0.30
    POSITIVE LOGITS
     Jr
    2.77
    Jr
    2.14
     jr
    2.11
     Sr
    1.88
     junior
    1.76
     Júnior
    1.69
     Junior
    1.68
     III
    1.63
     JR
    1.56
    junior
    1.49
    Activations Density 0.477%

    No Known Activations