© 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-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 31590
    Prev
    Next
    INDEX
    Explanations

    references to medical or biological assessments and conditions

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

    mathematical notation and specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Shepard
    -0.92
    ization
    -0.91
    ので
    -0.83
    phard
    -0.71
     Esch
    -0.71
     &___
    -0.70
    й
    -0.69
    siębior
    -0.69
    ————————————————
    -0.68
    osoever
    -0.68
    POSITIVE LOGITS
    ing
    1.44
    er
    1.22
     HasFactory
    1.00
    ING
    0.90
     tongs
    0.90
     تضيفلها
    0.87
    lapsingToolbar
    0.86
     Auvergne
    0.85
     Gert
    0.83
     Schult
    0.82
    Activations Density 0.870%

    No Known Activations