© 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. 22-GEMMASCOPE-RES-16K
    11. 11465
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and expressions indicating emotional reactions or personal thoughts

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

    Followed by a discourse marker/filler

    np_acts-logits-general · gemini-2.0-flash

    anyway after punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.77
    TintMode
    -0.76
     الرياضيه
    -0.75
     мәкал
    -0.68
     Zwar
    -0.63
    numerusform
    -0.62
     Dabei
    -0.61
    QMetaType
    -0.61
     zwar
    -0.59
     Embora
    -0.59
    POSITIVE LOGITS
    Anyway
    2.41
     Anyway
    2.34
     Anyways
    2.16
    Anyways
    2.13
    anyway
    2.09
     anyway
    2.07
    Anyhow
    2.00
     anyways
    1.92
     anyhow
    1.63
     digress
    1.57
    Activations Density 0.249%

    No Known Activations