© 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. 9-GEMMASCOPE-RES-131K
    11. 128779
    Prev
    Next
    INDEX
    Explanations

    references to ancient spiritual symbols and practices, particularly those related to Druids and runes

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    runic calendars and druidism

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    styleType
    -0.49
    reactstrap
    -0.49
     indisponible
    -0.49
    StoryboardSegue
    -0.48
    transQ
    -0.47
    ymce
    -0.47
     stanga
    -0.46
    tagHelperRunner
    -0.46
     Thir
    -0.46
    PickerController
    -0.43
    POSITIVE LOGITS
     runes
    1.81
     rune
    1.79
     Rune
    1.56
    Rune
    1.56
    rune
    1.23
     run
    0.73
     Run
    0.66
     RUN
    0.65
     runners
    0.64
     talisman
    0.63
    Activations Density 0.014%

    No Known Activations