© 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. 16099
    Prev
    Next
    INDEX
    Explanations

    quantitative descriptors indicating abundance or quantity

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

    preceding comparative adjectives or adverbs

    np_acts-logits-general · gemini-2.0-flash

    much, many, very, long

    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
    帖最后由
    -0.91
     שוליים
    -0.84
    endphp
    -0.84
     pinulongan
    -0.83
     intptr
    -0.78
    发表于
    -0.77
     esternos
    -0.76
    }{*}{}
    -0.74
    NUMX
    -0.74
    >--}}
    -0.74
    POSITIVE LOGITS
    ,
    1.00
    yyyy
    0.73
    yyy
    0.67
    yyyyy
    0.63
    rrrr
    0.62
    yy
    0.62
    eeee
    0.62
    eee
    0.60
     freaking
    0.58
    ・
    0.56
    Activations Density 0.155%

    No Known Activations