© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6493
    Prev
    Next
    INDEX
    Explanations

    the beginning of new sections or paragraphs in a document

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

    start of document markers or section beginnings (specifically the <bos> token).

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
    <eos>
    -0.56
     
    -0.52
    al
    -0.48
     The
    -0.45
    r
    -0.45
    2
    -0.45
    l
    -0.45
    _
    -0.45
    g
    -0.45
    The
    -0.44
    POSITIVE LOGITS
     autorytatywna
    0.83
     nahilalakip
    0.83
    Diweddarwch
    0.67
    enterOuterAlt
    0.65
    devamını
    0.60
    iſten
    0.59
    majánló
    0.59
     kasarigan
    0.58
    iſen
    0.58
     ſind
    0.57
    Activations Density 0.051%

    No Known Activations