© 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. 15627
    Prev
    Next
    INDEX
    Explanations

    phrases related to clinical and regulatory processes

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

    Follows nouns

    np_acts-logits-general · gemini-2.0-flash

    reporting and procedural contexts

    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
     and
    -0.60
     propOrder
    -0.57
    хьтан
    -0.54
    المناصب
    -0.54
    rungsseite
    -0.53
     &
    -0.52
    PreInfinity
    -0.50
     Meksiku
    -0.50
    richTextPanel
    -0.50
     or
    -0.49
    POSITIVE LOGITS
     alike
    0.80
     respectivamente
    0.63
     serta
    0.57
     sowie
    0.57
     respectively
    0.53
     gleicher
    0.51
     zugleich
    0.50
    sowie
    0.50
     соответственно
    0.47
     दोनों
    0.46
    Activations Density 1.274%

    No Known Activations