© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 7725
    Prev
    Next
    INDEX
    Explanations

    financial and operational details regarding healthcare and legal expenses

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Payments, funding, and expenses

    np_acts-logits-general · gemini-2.0-flash

    payment and funding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    subplots
    -0.33
     lượt
    -0.33
     Akhir
    -0.30
    atuor
    -0.30
     uy
    -0.29
    کید
    -0.29
     natt
    -0.28
    midos
    -0.28
    binant
    -0.28
    Accessor
    -0.28
    POSITIVE LOGITS
     funded
    1.63
     financed
    1.61
     funding
    1.48
    funded
    1.41
     financing
    1.30
     Funded
    1.30
     financi
    1.28
    Funding
    1.26
    funding
    1.26
     Funding
    1.24
    Activations Density 0.476%

    No Known Activations