© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13523
    Prev
    Next
    INDEX
    Explanations

    concepts related to energy efficiency and cost reduction

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

    Energy efficiency and fuel consumption

    np_acts-logits-general · gemini-2.0-flash

    energy efficiency and savings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     Chwiliwch
    -0.39
     dirty
    -0.35
    Personendaten
    -0.35
     swiftly
    -0.34
    dirty
    -0.33
     "
    -0.33
     Mühl
    -0.33
    ired
    -0.33
     c
    -0.32
    Originally
    -0.32
    POSITIVE LOGITS
     TextAppearance
    0.66
     MainAxisSize
    0.65
     énergétique
    0.64
     énergé
    0.59
     économies
    0.54
     économ
    0.54
     ahorrar
    0.54
     المعيارى
    0.54
     savings
    0.54
     éco
    0.53
    Activations Density 0.189%

    No Known Activations