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

    Neuronpedia

    Jacobian LensNEW
    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. 20-GEMMASCOPE-RES-16K
    11. 8517
    Prev
    Next
    INDEX
    Explanations

    greetings and polite expressions in communication

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

    Formal greetings and expressions of gratitude

    np_acts-logits-general · gemini-2.0-flash

    greetings and thanks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     but
    -0.60
    aarrggbb
    -0.59
    anskje
    -0.55
    Jvm
    -0.51
    但她
    -0.50
    لكن
    -0.50
     But
    -0.49
    ср
    -0.48
    醐
    -0.48
    不過
    -0.48
    POSITIVE LOGITS
    Hi
    1.65
    Dear
    1.46
     Hi
    1.42
    Hello
    1.40
     Hello
    1.34
     Dear
    1.30
     hello
    1.20
    Hey
    1.18
    hello
    1.14
     Hey
    1.11
    Activations Density 0.290%

    No Known Activations