Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 126597
    Prev
    Next
    INDEX
    Explanations

    references to the concept of promise or commitments in various contexts

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

    promise

    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
    -0.47
     In
    -0.43
    In
    -0.40
     at
    -0.39
     \
    -0.35
     Tại
    -0.35
     Marín
    -0.32
     as
    -0.32
     IN
    -0.32
     detectar
    -0.32
    POSITIVE LOGITS
     promise
    1.34
     Promise
    1.29
    promise
    1.17
    Promise
    1.13
     promessa
    1.13
     promises
    1.11
     promesa
    1.06
     Promises
    1.03
     promised
    1.02
     Promised
    0.95
    Activations Density 0.007%

    No Known Activations