© 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. 9630
    Prev
    Next
    INDEX
    Explanations

    phrases indicating statements or assertions

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

    Text after periods followed by unexpected characters

    np_acts-logits-general · gemini-2.0-flash

    punctuation followed by text

    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
    AsUp
    -0.78
     otomatig
    -0.71
    bibfield
    -0.63
     Họ
    -0.63
    Portail
    -0.62
    
    -0.60
    BibitemShut
    -0.59
    我也是
    -0.59
    PERATURE
    -0.59
     Mereka
    -0.58
    POSITIVE LOGITS
     Theore
    0.72
     Assuming
    0.70
     thereby
    0.67
    Assuming
    0.67
     assuming
    0.66
    ParallelGroup
    0.65
     Essentially
    0.65
    Effec
    0.64
     depending
    0.64
    Obviously
    0.64
    Activations Density 0.472%

    No Known Activations