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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 104896
    Prev
    Next
    INDEX
    Explanations

    terms related to commitments and assurances, particularly around pledges and promises

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

    pledge or voucher

    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
    in
    -0.56
     the
    -0.48
    ,
    -0.44
     Morin
    -0.43
     \\
    -0.43
    def
    -0.42
     ...
    -0.41
    begin
    -0.41
     Copeland
    -0.40
    ↵↵↵
    -0.39
    POSITIVE LOGITS
     Voucher
    1.09
    Voucher
    1.03
     voucher
    0.96
    ouchers
    0.89
    voucher
    0.87
     vouchers
    0.85
     queſta
    0.81
     pledge
    0.78
     Pledge
    0.78
    ðsíða
    0.77
    Activations Density 0.011%

    No Known Activations