© 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. 30097
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "took" and its variations, indicating a focus on actions or events that involve taking or acquiring

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

    took a

    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
     unittest
    -0.56
    PerformLayout
    -0.50
    ChildScrollView
    -0.45
    LikeLike
    -0.45
    存于互联网档案馆
    -0.43
    Germania
    -0.41
     bahía
    -0.41
     Dane
    -0.41
    digarh
    -0.41
     sánh
    -0.40
    POSITIVE LOGITS
    took
    0.80
     Took
    0.79
    Took
    0.77
    drew
    0.70
     took
    0.65
    Gave
    0.65
     Gave
    0.62
    threw
    0.62
    did
    0.60
     Moul
    0.60
    Activations Density 0.014%

    No Known Activations