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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 11131
    Prev
    Next
    INDEX
    Explanations

    references to churches and cathedrals, particularly those named after saints

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

    Saints and church names

    np_acts-logits-general · gemini-2.0-flash

    Names of saints

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     masses
    -0.37
    UrlEncoded
    -0.36
     Dulce
    -0.36
    uffff
    -0.35
     grown
    -0.35
    bitField
    -0.34
    adaptiveStyles
    -0.34
     spett
    -0.33
    ónio
    -0.32
    quesa
    -0.32
    POSITIVE LOGITS
    下载附件
    0.52
     Rehab
    0.50
     Rehabilitation
    0.50
    readystatechange
    0.47
    GEBUR
    0.47
     basili
    0.46
    nextSibling
    0.46
     LoggerFactory
    0.46
    Cyfarwyddwr
    0.46
    interopRequire
    0.46
    Activations Density 0.157%

    No Known Activations