© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 26675
    Prev
    Next
    INDEX
    Explanations

    concepts related to vows and commitments, particularly in the context of marriage or oaths

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    pledges, oaths, and vows

    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
    Negative Logits
     getItemCount
    -0.57
     createState
    -0.57
     BrowserModule
    -0.56
    CppCodeGen
    -0.55
    fjspx
    -0.53
     surla
    -0.53
     שוליים
    -0.50
    Bronnen
    -0.49
     interlocutor
    -0.48
    xase
    -0.48
    POSITIVE LOGITS
     pledge
    0.73
     commitment
    0.69
     oath
    0.65
     vow
    0.63
     pledging
    0.60
     Pledge
    0.59
     pledged
    0.58
     vows
    0.57
     pledges
    0.56
     commitments
    0.55
    Activations Density 0.030%

    No Known Activations