© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 10776
    Prev
    Next
    INDEX
    Explanations

    features related to product functionality and benefits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.51
     cheap
    -0.49
     utafitiHapana
    -0.45
    RegressionTest
    -0.44
     initComponents
    -0.44
     Cheap
    -0.43
    regeln
    -0.41
     ↓,
    -0.41
    )();
    -0.41
    Населення
    -0.41
    POSITIVE LOGITS
     effortlessly
    0.89
     effortless
    0.80
     fácilmente
    0.75
     comfortably
    0.68
     easily
    0.67
    AddTagHelper
    0.63
     confidently
    0.62
    Easily
    0.62
     Easily
    0.61
     seamlessly
    0.61
    Activations Density 0.512%

    No Known Activations