© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 14917
    Prev
    Next
    INDEX
    Explanations

    phrases related to expectations and claims about quality and service

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

    preceding "expect" or "expected"

    np_acts-logits-general · gemini-2.0-flash

    would expect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StoryboardSegue
    -0.54
    janja
    -0.53
    aarrggbb
    -0.52
    ulele
    -0.52
     sija
    -0.52
     Accessory
    -0.48
     crossorigin
    -0.47
    DockStyle
    -0.47
     cong
    -0.46
     Beschluss
    -0.46
    POSITIVE LOGITS
     expect
    3.16
    expect
    2.85
     expectation
    2.82
     Expect
    2.79
     expected
    2.79
     EXPECT
    2.79
     expects
    2.73
     expectations
    2.65
     expecting
    2.62
    Expect
    2.58
    Activations Density 0.334%

    No Known Activations