© 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. 31-GEMMASCOPE-RES-16K
    11. 3014
    Prev
    Next
    INDEX
    Explanations

    terms related to neurological processes and language deficits in children

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

    scientific and medical terminology related to neuroscience, brain imaging, and neurological research.

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

    technical and scientific language related to neuroimaging research, brain studies, and medical terminology.

    oai_token-act-pair · claude-4-5-haiku
    Triggered 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
    Negative Logits
    oredCriteria
    -0.54
    TypedDataSet
    -0.50
    ագրություններ
    -0.48
    findpost
    -0.47
    éndolo
    -0.43
    évaluateur
    -0.43
     Paglinawan
    -0.43
     للاسماء
    -0.42
     urbanas
    -0.41
    脚注の使い方
    -0.41
    POSITIVE LOGITS
     fMRI
    0.79
     brain
    0.77
     Brain
    0.66
     neuro
    0.63
    Brain
    0.63
     cortical
    0.59
    brain
    0.59
     BOLD
    0.58
     brains
    0.56
     Neuroscience
    0.56
    Activations Density 0.905%

    No Known Activations