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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 125256
    Prev
    Next
    INDEX
    Explanations

    references to "glory," particularly in a religious or spiritual context

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

    glory, glorious, Gloria

    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
    mtd
    -0.47
     n
    -0.45
    <
    -0.44
     useRef
    -0.39
    owieck
    -0.37
     inse
    -0.37
     ne
    -0.37
    N
    -0.36
    wapV
    -0.36
     some
    -0.36
    POSITIVE LOGITS
    glory
    1.20
    Glory
    1.09
     glory
    1.05
     Glory
    1.04
     gloire
    0.97
    Glorious
    0.94
    glor
    0.88
     gloria
    0.84
    Gloria
    0.84
     Glorious
    0.83
    Activations Density 0.003%

    No Known Activations