© 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. 8607
    Prev
    Next
    INDEX
    Explanations

    pronouns and their associations in sentences

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

    Followed by "you" or "re"

    np_acts-logits-general · gemini-2.0-flash

    you want or use

    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
    HomeAsUpEnabled
    -0.57
    Simply
    -0.56
    simply
    -0.56
    neither
    -0.54
    urably
    -0.54
    atissimo
    -0.51
     Wiktionnaire
    -0.50
     quietly
    -0.50
     simply
    -0.50
    不僅
    -0.50
    POSITIVE LOGITS
    WebServlet
    0.68
    ilibrium
    0.66
    Externé
    0.65
     originally
    0.64
    liesslich
    0.62
    قایناقلار
    0.61
    +#+#
    0.61
    Rujuakan
    0.60
     originalmente
    0.60
    GeneratedCode
    0.58
    Activations Density 0.321%

    No Known Activations