© 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
    4. Residual Stream - 16k
    5. 30-GEMMASCOPE-RES-16K
    6. 10602
    Prev
    Next
    INDEX
    Explanations

    references to holy or religious concepts, particularly related to the Holy Land or the Holy Roman Empire

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

    "Holy" followed by "Roman"

    np_acts-logits-general · gemini-2.0-flash

    Holy Roman Empire

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    verwijspagina
    -0.66
    MessageTagHelper
    -0.56
     Италијани
    -0.55
    tanleria
    -0.53
    UrlResolution
    -0.52
     Tasche
    -0.49
     ederim
    -0.48
    prefixer
    -0.46
    /*++
    -0.46
     Treue
    -0.46
    POSITIVE LOGITS
     Holy
    0.60
    Holy
    0.58
     holy
    0.57
    holy
    0.51
     HOLY
    0.50
    HOLY
    0.49
     grail
    0.49
     trinity
    0.46
    trinity
    0.45
     Trinity
    0.44
    Activations Density 0.062%

    No Known Activations