© 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. 1003
    Prev
    Next
    INDEX
    Explanations

    the letter 'S' in various contexts

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

    The letter "S" followed by punctuation or parentheses

    np_acts-logits-general · gemini-2.0-flash

    starts with S and followed by code/math symbols

    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
    bootstrapcdn
    -0.92
     pinulongan
    -0.92
    transQ
    -0.81
    
    -0.80
     kasarigan
    -0.78
    AnchorStyles
    -0.73
     الرياضيه
    -0.73
     EconPapers
    -0.72
    μως
    -0.71
    ondern
    -0.71
    POSITIVE LOGITS
    bardier
    0.40
    preventDefault
    0.39
    <bos>
    0.38
    ***
    0.38
    מני
    0.38
    クセ
    0.37
     deuter
    0.37
     d
    0.37
    3
    0.36
    utilisons
    0.36
    Activations Density 0.361%

    No Known Activations