© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12255
    Prev
    Next
    INDEX
    Explanations

    specific terms and formats related to scientific data reporting and mathematical equations

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

    scientific or technical document elements like tables, figures, equations, or references.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    Not in Any Lists

    No Comments

    Negative Logits
    IUrlHelper
    -0.98
     autorytatywna
    -0.77
    httphttps
    -0.71
     &___
    -0.70
    parsedMessage
    -0.68
    ValueStyle
    -0.66
    TypedDataSet
    -0.63
     ujednoznacz
    -0.61
    ьаж
    -0.61
     invokingState
    -0.59
    POSITIVE LOGITS
     Jerusalén
    0.55
     elaboración
    0.44
     bahía
    0.43
     enfance
    0.42
     herido
    0.42
     herida
    0.42
     religión
    0.41
     Moscú
    0.41
     húmedo
    0.40
     secundario
    0.40
    Activations Density 1.062%

    No Known Activations