© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 4796
    Prev
    Next
    INDEX
    Explanations

    medical terms related to treatment, patient outcomes, and specific trial results

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

    medical terminology and statistical/research language related to clinical studies.

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

    numerical percentages and statistical comparisons in medical research results.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    illaries
    -0.35
    [toxicity=0]
    -0.31
    Похо
    -0.31
    åter
    -0.30
    wnież
    -0.29
    estrian
    -0.29
     dessutom
    -0.29
    dir
    -0.29
     astfel
    -0.29
    ribute
    -0.29
    POSITIVE LOGITS
     versus
    3.63
     vs
    3.61
     Versus
    2.95
    versus
    2.86
     Vs
    2.75
     VS
    2.48
    vs
    2.44
    Versus
    2.34
    VS
    1.76
    Vs
    1.73
    Activations Density 1.187%

    No Known Activations