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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 111263
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to engagement and proposals in relationships

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

    engagement and commitment

    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
    ########.
    -0.40
     mái
    -0.40
    tys
    -0.38
    type
    -0.38
     BOC
    -0.37
    CellStyle
    -0.35
    types
    -0.35
     Ludwig
    -0.35
    Portale
    -0.34
    átiles
    -0.34
    POSITIVE LOGITS
     fiance
    0.72
     fiancé
    0.66
     fidanz
    0.65
     fiancée
    0.64
    lorette
    0.63
     Engagement
    0.62
    💍
    0.62
     betro
    0.61
     MatDialog
    0.61
    HomeAsUpEnabled
    0.60
    Activations Density 0.003%

    No Known Activations