© 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. 79960
    Prev
    Next
    INDEX
    Explanations

    expressions of affirmation or confirmation

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

    already

    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
     siège
    -0.38
    S
    -0.37
     seat
    -0.33
    F
    -0.30
    i
    -0.30
    談社
    -0.29
     funds
    -0.29
     asiento
    -0.29
    C
    -0.28
     діяльності
    -0.28
    POSITIVE LOGITS
    Sudah
    1.09
     Already
    1.03
     Sudah
    0.99
     Уже
    0.98
    already
    0.98
    Already
    0.98
    Уже
    0.95
     already
    0.94
     ALREADY
    0.92
     sudah
    0.91
    Activations Density 0.011%

    No Known Activations