© 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. 7-GEMMASCOPE-RES-16K
    11. 15553
    Prev
    Next
    INDEX
    Explanations

    references to the concept of time spent or investment in various activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     confirmer
    -0.58
     courriel
    -0.52
     חד
    -0.50
    Algemeen
    -0.48
    MathML
    -0.48
     chassis
    -0.47
    IconModule
    -0.47
     Keil
    -0.47
    verwijspagina
    -0.47
     hulp
    -0.47
    POSITIVE LOGITS
     spend
    2.31
     spent
    2.08
    Spend
    2.08
    spend
    2.08
     Spend
    2.06
     spending
    2.05
     spends
    2.02
    Spending
    2.00
    spent
    1.94
     Spending
    1.90
    Activations Density 0.093%

    No Known Activations