© 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. 122212
    Prev
    Next
    INDEX
    Explanations

    affirmations of ideas and suggestions being discussed

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

    reporting speech or actions

    np_acts-logits-general · gemini-2.5-flash-lite

    phrases that directly address the reader with thanks, praise, or appreciation (compliments and polite acknowledgements).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
     تضيفلها
    -0.42
     ब्रेकडाउन
    -0.40
    RenderAtEndOf
    -0.37
    パード
    -0.35
    شهاد
    -0.33
     Woodward
    -0.32
    İstinadlar
    -0.32
    SpringBootTest
    -0.31
    :✨
    -0.31
    WireFormat
    -0.31
    POSITIVE LOGITS
    richTextPanel
    0.54
     GLFW
    0.52
    asztal
    0.48
     avoient
    0.48
     tabPage
    0.47
     amitié
    0.47
     eccell
    0.46
    つもり
    0.45
    softc
    0.45
     intéressant
    0.45
    Activations Density 0.249%

    No Known Activations