© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 122780
    Prev
    Next
    INDEX
    Explanations

    speculative statements or expressions of anticipation

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

    expect and its forms

    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
     Waterman
    -0.49
     “
    -0.42
     Mullen
    -0.40
     
    -0.40
     McNally
    -0.39
    ’
    -0.39
     Grimes
    -0.38
     Dunham
    -0.38
     in
    -0.38
     ‘
    -0.38
    POSITIVE LOGITS
    expect
    1.32
     Expect
    1.30
     expect
    1.25
    Expect
    1.23
     EXPECT
    1.13
     expectancy
    1.01
     expecting
    0.99
     expects
    0.99
    Expecting
    0.97
     Expected
    0.95
    Activations Density 0.031%

    No Known Activations