© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 1662
    Prev
    Next
    INDEX
    Explanations

    terms related to massage therapy

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

    terms related to massage therapy and relaxation

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

    physical comfort and massage

    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
     faim
    -0.53
     Anz
    -0.52
     Pank
    -0.52
    lader
    -0.50
     famine
    -0.49
     Landwirtschaft
    -0.49
     cag
    -0.48
    Coro
    -0.47
    viato
    -0.47
    ENCY
    -0.47
    POSITIVE LOGITS
     massage
    1.53
     Massage
    1.48
    Massage
    1.39
    massage
    1.23
     massages
    1.23
     masaj
    1.13
     masse
    1.06
     masaje
    1.06
    按摩
    0.96
     Jacuzzi
    0.91
    Activations Density 0.026%

    No Known Activations