© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9980
    Prev
    Next
    INDEX
    Explanations

    statements related to health, well-being, and scientific studies concerning these topics

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

    periods and sentence-ending punctuation that conclude informative or factual statements.

    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
     defaultstate
    -0.50
     estekak
    -0.49
    wapV
    -0.48
    MultipartFile
    -0.47
    IndentedString
    -0.47
    GHIJKLM
    -0.46
    ksjoner
    -0.45
     mukana
    -0.43
    IntoConstraints
    -0.42
    WithIOException
    -0.42
    POSITIVE LOGITS
     studies
    2.27
    studies
    1.88
    Studies
    1.83
     Studies
    1.81
     research
    1.80
     STUDIES
    1.64
     researches
    1.63
     estudios
    1.55
     Studien
    1.52
     estudos
    1.49
    Activations Density 1.293%

    No Known Activations