© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 6241
    Prev
    Next
    INDEX
    Explanations

    terms and references related to guns and genetic concepts

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

    "Gene" as the first word

    np_acts-logits-general · gemini-2.0-flash

    gene expression, therapy, or hunt

    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
    ^(@)
    -0.90
    脚注の使い方
    -0.77
     myſelf
    -0.75
     Theſe
    -0.75
    WriteBarrier
    -0.74
    wiſe
    -0.73
     Monfieur
    -0.73
    Rhestr
    -0.73
     Anſ
    -0.72
     iſt
    -0.72
    POSITIVE LOGITS
     aDecoder
    0.67
     réf
    0.58
    ign
    0.53
    powder
    0.52
    moke
    0.52
    boat
    0.51
    yargs
    0.51
    率
    0.51
    ny
    0.50
     maș
    0.50
    Activations Density 0.153%

    No Known Activations