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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 39-GEMMASCOPE-RES-16K
    11. 3143
    Prev
    Next
    INDEX
    Explanations

    phrases related to reducing energy consumption and waste

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     barato
    -0.37
    Understanding
    -0.36
     Würde
    -0.34
    accordo
    -0.34
    understanding
    -0.34
     peace
    -0.33
    ChildIndex
    -0.33
     Understanding
    -0.33
     sabiduría
    -0.33
    ough
    -0.32
    POSITIVE LOGITS
     costs
    0.78
     dependence
    0.73
     overall
    0.72
     wastage
    0.71
     complexity
    0.71
     reliance
    0.71
     risk
    0.70
     expenses
    0.69
     dependency
    0.69
    costs
    0.68
    Activations Density 0.685%

    No Known Activations