© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 38477
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a strong dedication or promise towards a cause or initiative

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

    commitment to a 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
     Савезне
    -0.42
     nurse
    -0.34
     usher
    -0.33
     Anderson
    -0.33
     later
    -0.33
    else
    -0.33
     Police
    -0.33
    ϴ
    -0.33
     reader
    -0.33
     user
    -0.33
    POSITIVE LOGITS
     commitment
    1.34
     Commitment
    1.27
    Commitment
    1.25
    commitment
    1.20
     commitments
    1.20
     Commit
    1.12
     commit
    1.05
     COMMIT
    1.05
    commit
    1.03
     commits
    1.01
    Activations Density 0.010%

    No Known Activations