© 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. 2-GEMMASCOPE-RES-16K
    6. 7915
    Prev
    Next
    INDEX
    Explanations

    references to various religious institutions, specifically the Church

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    migrationBuilder
    -0.48
    HomeAsUpEnabled
    -0.44
     ब्रेकडाउन
    -0.43
     contacts
    -0.43
    انجليز
    -0.43
    ImageContext
    -0.42
    verwijspagina
    -0.42
    cesis
    -0.41
    webElementXpaths
    -0.41
    RefNanny
    -0.41
    POSITIVE LOGITS
     CHURCH
    1.28
     church
    1.25
    Church
    1.18
    church
    1.18
     Church
    1.17
    CHURCH
    1.16
     iglesia
    0.88
     igreja
    0.84
     kerk
    0.81
    église
    0.71
    Activations Density 0.124%

    No Known Activations