Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 21839
    Prev
    Next
    INDEX
    Explanations

    mentions and references to parishes and their roles

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

    parish church and priest

    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
    Hitler
    -0.52
    SIGNED
    -0.51
     فريبيس
    -0.51
     Cleopatra
    -0.50
     Mussolini
    -0.49
     Hitler
    -0.49
     informée
    -0.49
    instrumental
    -0.49
    Remover
    -0.47
     estekak
    -0.47
    POSITIVE LOGITS
     Parish
    1.03
     parish
    1.02
    Parish
    0.88
     parishes
    0.76
     paroisse
    0.75
     Parrish
    0.69
     Pfarr
    0.69
     parishi
    0.61
     district
    0.60
     parroquia
    0.59
    Activations Density 0.005%

    No Known Activations