© 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. 7998
    Prev
    Next
    INDEX
    Explanations

    phrases related to funding and financial mechanisms

    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
    енча
    -0.55
    httphttps
    -0.48
     onBind
    -0.48
    endregion
    -0.47
    Климат
    -0.45
    :✨
    -0.44
    enedig
    -0.42
    RatingBar
    -0.41
     expensive
    -0.41
     EClass
    -0.40
    POSITIVE LOGITS
     funds
    1.26
     proceeds
    1.20
     fund
    1.05
     Funds
    1.04
    funds
    1.02
    Funds
    1.00
     monies
    0.93
     Proceeds
    0.93
     FUNDS
    0.93
     fondos
    0.88
    Activations Density 0.525%

    No Known Activations