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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 5333
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and markers of conclusions or summarizations

    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
    الحياه
    -0.62
    이고
    -0.42
     &___
    -0.42
     mà
    -0.41
     ***!
    -0.40
    Rüyada
    -0.39
    parsedMessage
    -0.38
    ItemBackground
    -0.38
    Бахар
    -0.37
    Personensuche
    -0.36
    POSITIVE LOGITS
     however
    3.63
     However
    2.91
    however
    2.86
    However
    2.81
     entanto
    2.64
     però
    2.55
     tuttavia
    2.50
     cependant
    2.48
     jedoch
    2.47
     однако
    2.45
    Activations Density 1.068%

    No Known Activations