© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 841
    Prev
    Next
    INDEX
    Explanations

    brands and products related to biotechnology and molecular biology

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

    scientific and laboratory technology brand names, especially from Life Technologies.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    mentions of commercial molecular biology vendors and their branded reagents, kits, and instruments.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    references to Life Technologies (a biotechnology company) and related scientific product names or catalog numbers.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    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
    UnitTesting
    -0.58
    expandindo
    -0.46
    Skocz
    -0.44
    InputBorder
    -0.43
     acorns
    -0.42
    '][]
    -0.42
    点此举报
    -0.42
    ksikon
    -0.42
    KommentareTeilen
    -0.42
    InSection
    -0.42
    POSITIVE LOGITS
     torchvision
    0.89
     torch
    0.66
    torch
    0.64
    ToTensor
    0.56
     Torch
    0.55
    pytorch
    0.54
     TOR
    0.53
     Мексичка
    0.52
    PropertyChanging
    0.50
    Torch
    0.50
    Activations Density 0.054%

    No Known Activations