© 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. 35-GEMMASCOPE-RES-16K
    11. 10502
    Prev
    Next
    INDEX
    Explanations

    specific phrases and terms related to medical treatments and dosing protocols

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     שוליים
    -0.36
    AnchorStyles
    -0.31
    PCell
    -0.29
    省市镇
    -0.29
     Normdatei
    -0.29
     CreateTagHelper
    -0.28
     információk
    -0.28
     насељу
    -0.27
     useParams
    -0.27
     Inhalte
    -0.27
    POSITIVE LOGITS
     rounds
    1.41
     round
    1.23
     iteration
    1.20
     cycles
    1.16
     batch
    1.13
     Rounds
    1.12
     cycle
    1.09
     batches
    1.07
     iterations
    1.06
     ROUND
    1.05
    Activations Density 1.056%

    No Known Activations