© 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
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 106095
    Prev
    Next
    INDEX
    Explanations

    commitments and promises regarding actions and agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     PopupWindow
    -0.41
    localtime
    -0.40
    twimg
    -0.39
     Cow
    -0.37
     Wat
    -0.37
    lemény
    -0.36
    Bronnen
    -0.35
     kasarigan
    -0.35
     DataTypes
    -0.35
     File
    -0.35
    POSITIVE LOGITS
     promise
    1.22
     promesa
    1.11
     promises
    1.05
     promised
    1.04
     promessa
    1.02
    promise
    1.00
     pledge
    0.97
     Promise
    0.97
     promesse
    0.96
     pledges
    0.96
    Activations Density 0.034%

    No Known Activations