© 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. 118
    Prev
    Next
    INDEX
    Explanations

    terms related to heat and thermal dynamics

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

    references to thermal energy or heat-related concepts

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

    heat current

    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
    GeneratedCode
    -0.48
    értel
    -0.45
    dium
    -0.44
    xmlWriter
    -0.44
    ppus
    -0.44
    amable
    -0.43
    thold
    -0.42
    uml
    -0.42
     katt
    -0.41
    arita
    -0.41
    POSITIVE LOGITS
     cherchés
    0.78
     الدولى
    0.71
    下载附件
    0.71
     snippetHide
    0.64
    سطس
    0.61
     Monfieur
    0.61
    ValueStyle
    0.61
     myſelf
    0.60
     Majefty
    0.56
    findpost
    0.54
    Activations Density 0.109%

    No Known Activations