© 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
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 5880
    Prev
    Next
    INDEX
    Explanations

    the word "expect" in various contexts, indicating predictions or expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    🩹
    -0.37
     bài
    -0.35
    ReusableCell
    -0.35
     surla
    -0.35
    ళ
    -0.34
     NavController
    -0.34
    complexContent
    -0.34
    ania
    -0.33
     Mullen
    -0.33
     "_"
    -0.32
    POSITIVE LOGITS
     expect
    4.13
     Expect
    3.67
    expect
    3.56
    Expect
    3.53
     expects
    3.16
     EXPECT
    3.16
     expecting
    3.06
     expectation
    2.80
     expected
    2.69
     expectations
    2.53
    Activations Density 0.083%

    No Known Activations