© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 11857
    Prev
    Next
    INDEX
    Explanations

    terms related to energy efficiency and usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    after "Energy" or related to "Energy"

    np_acts-logits-general · gemini-2.0-flash

    energy Star

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegistryLite
    -0.92
    MockBean
    -0.68
     getItemCount
    -0.65
    RegressionTest
    -0.64
    writeFieldEnd
    -0.60
     []),
    -0.60
    VolleyError
    -0.59
     otomatig
    -0.58
    StoryboardSegue
    -0.58
    webElementXpaths
    -0.56
    POSITIVE LOGITS
     drink
    0.70
     drinks
    0.69
     Drink
    0.66
    efficient
    0.63
    drink
    0.62
     Sonnen
    0.60
    Palabras
    0.60
     Efficient
    0.59
     efficiency
    0.57
    ReusableCell
    0.57
    Activations Density 0.085%

    No Known Activations