© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 1770
    Prev
    Next
    INDEX
    Explanations

    terms related to thermodynamics and energy exchange processes

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

    physical or quantum systems

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    rungsseite
    -0.66
    URLException
    -0.56
    хьтан
    -0.52
    skjaer
    -0.48
     старости
    -0.47
     Sequencing
    -0.47
     Endurance
    -0.47
    advent
    -0.45
    avadoc
    -0.45
    paedic
    -0.44
    POSITIVE LOGITS
     system
    1.57
     systems
    1.55
    system
    1.31
     System
    1.26
    systems
    1.26
     subsystems
    1.23
     Systems
    1.23
     SYSTEM
    1.20
    Systems
    1.18
    システム
    1.18
    Activations Density 0.302%

    No Known Activations