© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 10879
    Prev
    Next
    INDEX
    Explanations

    phrases indicating anticipation or expectation of outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    -0.41
     caneta
    -0.39
     individuales
    -0.39
     privada
    -0.39
    ownic
    -0.39
     aislado
    -0.38
     aislada
    -0.38
    private
    -0.37
    s
    -0.36
     personalizado
    -0.36
    POSITIVE LOGITS
     Expect
    1.41
    expect
    1.38
     expect
    1.34
    Expect
    1.32
     EXPECT
    1.30
     expectation
    1.23
     Expectations
    1.22
     Expectation
    1.20
     expectancy
    1.20
     expectations
    1.19
    Activations Density 0.074%

    No Known Activations