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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 64158
    Prev
    Next
    INDEX
    Explanations

    concepts and discussions surrounding faith and belief systems

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

    is conditional

    np_acts-logits-general · gemini-2.5-flash-lite

    language that signals logical inference and conditional reasoning, marking claims, implications, and evidential assertions in argumentative text.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    HasForeignKey
    -0.49
    MessageOf
    -0.48
    prepareStatement
    -0.47
    ⤹
    -0.46
     COMPUT
    -0.46
    LARATION
    -0.46
    ingtones
    -0.44
    تقاوى
    -0.44
     ब्रेकडाउन
    -0.44
    wapV
    -0.44
    POSITIVE LOGITS
    GEBURTSDATUM
    0.46
    httphttps
    0.40
     BoxDecoration
    0.38
    Nationalité
    0.35
     않습니다
    0.34
    Искәрмәләр
    0.34
    kháu
    0.34
     sostenibilidad
    0.32
     anzu
    0.31
     MainAxisSize
    0.31
    Activations Density 0.121%

    No Known Activations