© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 476
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to worship and spiritual practice

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

    Preceding personal pronouns

    np_acts-logits-general · gemini-2.0-flash

    Vishnu, Narasimha. He has

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    muir
    -0.54
     Faw
    -0.51
     flamb
    -0.49
    彰
    -0.48
     wo
    -0.47
     Mers
    -0.47
     Alhambra
    -0.47
    neo
    -0.47
     Alab
    -0.47
     فارس
    -0.46
    POSITIVE LOGITS
     autorytatywna
    0.52
     pureza
    0.51
     énergétique
    0.49
     Vorles
    0.48
     électroniques
    0.48
     Psicología
    0.46
     colecciones
    0.46
    Autoritní
    0.46
     inoxidable
    0.44
     dentaire
    0.44
    Activations Density 0.166%

    No Known Activations