© 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. 11433
    Prev
    Next
    INDEX
    Explanations

    mathematical statements related to polynomial conditions and functions

    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
     InputDecoration
    -0.59
    RTLR
    -0.56
     informée
    -0.54
     चीज़ों
    -0.54
    RTLI
    -0.52
    ագրություններ
    -0.50
    Життєпис
    -0.50
    béco
    -0.49
    parsedMessage
    -0.48
    topping
    -0.48
    POSITIVE LOGITS
     holds
    0.88
     hold
    0.70
     Holds
    0.69
     implies
    0.65
    holds
    0.62
     satisfied
    0.61
     HOLD
    0.56
     Hold
    0.56
     statement
    0.56
     condition
    0.56
    Activations Density 2.556%

    No Known Activations