© 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. 1233
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to statistics and experimental methods

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

    Follows words like "lymph", "urban", or "matrix"

    np_acts-logits-general · gemini-2.0-flash

    medical and material classification terms

    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
     noDo
    -0.48
     econó
    -0.47
     economically
    -0.46
    rungsseite
    -0.46
     tempore
    -0.46
    SessionFactory
    -0.46
    französ
    -0.45
     تعدى
    -0.44
     <
    -0.44
     situe
    -0.44
    POSITIVE LOGITS
     etc
    1.34
     usw
    1.18
    etc
    1.10
     itp
    0.98
    などなど
    0.97
     Etc
    0.93
     nahilalakip
    0.89
     osv
    0.86
    Etc
    0.84
    等等
    0.83
    Activations Density 1.369%

    No Known Activations