© 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. 8094
    Prev
    Next
    INDEX
    Explanations

    phrases that express surprise or exclamation

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

    Interjections like "oh," "ah," and foreign equivalents

    np_acts-logits-general · gemini-2.0-flash

    exclamations of surprise or acknowledgment

    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
     iſt
    -0.66
     fubject
    -0.65
     purpoſe
    -0.64
    Personendaten
    -0.63
     juſ
    -0.62
    ---+
    -0.62
     poffible
    -0.62
     quæ
    -0.61
     niyang
    -0.61
     raiſ
    -0.60
    POSITIVE LOGITS
     oh
    1.70
     Oh
    1.63
    Oh
    1.52
    oh
    1.44
     ah
    1.39
     Ah
    1.34
     oops
    1.32
    Ah
    1.32
     Ahh
    1.31
    Ahh
    1.29
    Activations Density 0.253%

    No Known Activations