© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 99079
    Prev
    Next
    INDEX
    Explanations

    references to a sense of calling or vocation, especially in a religious or ministerial context

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

    calling and vowing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UrlResolution
    -0.44
     Benutz
    -0.40
    balleur
    -0.39
    โล
    -0.35
     andern
    -0.35
     emoción
    -0.33
    guard
    -0.32
    <tfoot>
    -0.32
     countrymen
    -0.32
     سكان
    -0.32
    POSITIVE LOGITS
     vocation
    0.72
     Voc
    0.56
    vocations
    0.55
     vocational
    0.54
    transQ
    0.54
    beruf
    0.53
    vocation
    0.52
    iprot
    0.50
    Voc
    0.49
    oł
    0.49
    Activations Density 0.100%

    No Known Activations