© 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. 15800
    Prev
    Next
    INDEX
    Explanations

    quantitative data related to percentage changes and financial figures

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

    Percentage or numerical increase/decrease

    np_acts-logits-general · gemini-2.0-flash

    percentages and amounts

    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
    principalTable
    -0.70
    DialogResult
    -0.69
    AddHtmlAttribute
    -0.67
    /**
    -0.65
     EconPapers
    -0.65
    Hauptartikel
    -0.62
     Garde
    -0.61
    ]")]
    -0.60
    hdashline
    -0.58
    IBinder
    -0.58
    POSITIVE LOGITS
     year
    0.68
     over
    0.67
     Paglinawan
    0.57
    EndContext
    0.56
    year
    0.54
     année
    0.54
     Year
    0.54
     YO
    0.53
     año
    0.53
    Year
    0.53
    Activations Density 0.147%

    No Known Activations