© 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. 3-GEMMASCOPE-RES-16K
    11. 8695
    Prev
    Next
    INDEX
    Explanations

    instances of the word "spend" or its variations, indicating a focus on time-related actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     initComponents
    -0.76
    Personendaten
    -0.56
    #+#
    -0.53
     للمعارف
    -0.52
    gridx
    -0.50
    queryInterface
    -0.50
     CreateTagHelper
    -0.50
    Примечания
    -0.48
    peteer
    -0.48
    RegressionTest
    -0.46
    POSITIVE LOGITS
     spend
    3.88
     Spend
    3.34
    spend
    3.33
     spends
    3.30
    Spend
    3.27
     spending
    3.14
     spent
    3.13
    Spending
    2.92
     Spending
    2.91
     Spent
    2.77
    Activations Density 0.051%

    No Known Activations