Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 30-GEMMASCOPE-RES-16K
    6. 12553
    Prev
    Next
    INDEX
    Explanations

    references to alternative lifestyles or philosophies

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

    Yoga, spirituality, and alternative medicine

    np_acts-logits-general · gemini-2.0-flash

    yoga and meditation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pflicht
    -0.40
     Wartung
    -0.40
     Beobachtung
    -0.39
     Verteilung
    -0.39
     Untersch
    -0.38
     εύ
    -0.38
     Vergnügen
    -0.38
     béisbol
    -0.38
     pungkasnya
    -0.37
    UpdateCommand
    -0.36
    POSITIVE LOGITS
     yoga
    1.43
     meditation
    1.37
     Yoga
    1.34
    yoga
    1.30
     spiritual
    1.28
    Yoga
    1.24
     Meditation
    1.21
     yog
    1.18
     Spiritual
    1.18
    spiritual
    1.16
    Activations Density 0.477%

    No Known Activations