© 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. 24-GEMMASCOPE-RES-16K
    11. 2879
    Prev
    Next
    INDEX
    Explanations

    keywords related to energy efficiency and air conditioning systems

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

    Air and ventilation systems

    np_acts-logits-general · gemini-2.0-flash

    air ventilation airflow fans

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    titleMargin
    -0.69
    saraba
    -0.68
    tagHelperRunner
    -0.67
    хьтан
    -0.66
    MessageState
    -0.65
    Jeografia
    -0.64
     SwitchCompat
    -0.63
     autorytatywna
    -0.63
    دانشنامهٔ
    -0.57
    تقاوى
    -0.57
    POSITIVE LOGITS
     air
    1.28
     ventilation
    1.27
     airflow
    1.23
     fan
    1.20
     fans
    1.19
     venti
    1.07
     Fans
    1.06
     Ventilation
    1.05
    Ventilation
    1.00
    fans
    1.00
    Activations Density 0.187%

    No Known Activations