© 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. 978
    Prev
    Next
    INDEX
    Explanations

    the presence of specific character patterns or placeholders indicating variables

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

    "5" followed by other tokens, potentially years or numerical values

    np_acts-logits-general · gemini-2.0-flash

    number and unit

    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
     skall
    -1.04
     herewith
    -0.91
    एँ
    -0.88
     läßt
    -0.84
     mußten
    -0.82
     Whilst
    -0.82
     Ministre
    -0.79
     hereof
    -0.79
    Whilst
    -0.78
     पहु
    -0.78
    POSITIVE LOGITS
     bosses
    0.90
     
    0.68
     

    0.67
     amid
    0.63
     coronavirus
    0.58
     
    0.58
     boss
    0.56
     Mr
    0.56
     chiefs
    0.56
     —
    0.55
    Activations Density 0.236%

    No Known Activations