© 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. 109678
    Prev
    Next
    INDEX
    Explanations

    references to promises and commitments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    marginVertical
    -0.36
    localtime
    -0.35
    Bronnen
    -0.35
    lemény
    -0.35
     Sicht
    -0.33
     shade
    -0.32
     author
    -0.31
     Gray
    -0.31
     Gesellschaft
    -0.30
     Völker
    -0.30
    POSITIVE LOGITS
     promise
    1.20
     promesa
    1.17
     promises
    1.11
     promised
    1.04
     promesse
    1.02
     promessa
    1.00
    promise
    1.00
     Promises
    0.98
     Promise
    0.98
    Promise
    0.96
    Activations Density 0.038%

    No Known Activations