© 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. 20-GEMMASCOPE-RES-16K
    11. 16209
    Prev
    Next
    INDEX
    Explanations

    expressions of urgency and frustration in informal communication

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

    Imperative sentences and requests

    np_acts-logits-general · gemini-2.0-flash

    please and requests

    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
    étrie
    -0.63
    '][]
    -0.61
    LEncoder
    -0.60
    WithIOException
    -0.59
     {}));
    -0.59
    まさに
    -0.58
    kloped
    -0.58
    MLLoader
    -0.57
    ("")]
    -0.57
    utched
    -0.56
    POSITIVE LOGITS
     please
    1.11
    please
    0.96
     PLEASE
    0.88
     plz
    0.86
    Please
    0.85
     dammit
    0.82
     Please
    0.81
     pls
    0.78
     bitte
    0.75
     пожалуйста
    0.75
    Activations Density 0.235%

    No Known Activations