© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 42414
    Prev
    Next
    INDEX
    Explanations

    elements and attributes related to various forms of spiritual or religious practice

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

    sarva, pūja, kharaj, āyudhams,uyện

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     nearly
    -0.35
     Photocase
    -0.35
    Nearly
    -0.33
    Casi
    -0.33
    Had
    -0.33
    ịp
    -0.32
    More
    -0.30
     lector
    -0.29
    连忙
    -0.29
    nearly
    -0.29
    POSITIVE LOGITS
    :✨
    0.70
    NameInMap
    0.65
    LookAnd
    0.65
    MigrationBuilder
    0.65
     AssemblyCulture
    0.61
     transfieras
    0.60
     isComment
    0.60
    botines
    0.60
    OGND
    0.59
    transQ
    0.58
    Activations Density 0.045%

    No Known Activations