© 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. 5637
    Prev
    Next
    INDEX
    Explanations

    HTML tags and their attributes in the document

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

    HTML tags

    np_acts-logits-general · gemini-2.0-flash

    HTML structure tags

    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
     Efq
    -0.80
    LookAnd
    -0.79
     Audiodateien
    -0.78
    AccessorTable
    -0.76
    EndProject
    -0.75
    ]='\
    -0.74
     <<<<<<<<<<<<<<
    -0.74
     fubject
    -0.73
    */)
    -0.73
    GraphicsUnit
    -0.72
    POSITIVE LOGITS
    div
    1.01
    span
    0.89
     p
    0.79
     div
    0.75
    p
    0.74
    ul
    0.71
    br
    0.70
    img
    0.69
     span
    0.68
     br
    0.68
    Activations Density 0.321%

    No Known Activations