© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 49048
    Prev
    Next
    INDEX
    Explanations

    species names and their classifications within biological taxonomy

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

    species of plant and animal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    TypedDataSet
    -0.66
    IVEREF
    -0.63
     estekak
    -0.61
    BufferException
    -0.54
     ویکی‌پدی
    -0.52
     createSlice
    -0.51
    лтемелер
    -0.50
     Италијани
    -0.49
    AISSEE
    -0.48
    layoutControl
    -0.48
    POSITIVE LOGITS
     sauvage
    0.55
     sauvages
    0.54
     guapos
    0.53
     species
    0.51
     hyvin
    0.50
     détermin
    0.48
     ejemplares
    0.48
     industriels
    0.47
     bomberos
    0.47
     spécifique
    0.47
    Activations Density 0.016%

    No Known Activations