© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 4505
    Prev
    Next
    INDEX
    Explanations

    references to awards and notable individuals in the context of artistic or intellectual achievements

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

    Word preceding a person's name/title

    np_acts-logits-general · gemini-2.0-flash

    authors and their works

    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
    MigrationBuilder
    -0.67
    wußt
    -0.62
    libft
    -0.55
    iseite
    -0.55
    adaptiveStyles
    -0.52
    Життєпис
    -0.51
    arsen
    -0.50
    gatsby
    -0.50
    enschappelijke
    -0.50
     useState
    -0.49
    POSITIVE LOGITS
     للاسماء
    0.65
     authors
    0.57
     philosopher
    0.56
     extraordinaire
    0.56
     author
    0.55
     novelist
    0.55
     theologian
    0.54
     poet
    0.52
     celebridades
    0.52
     neutrinos
    0.51
    Activations Density 0.253%

    No Known Activations