© 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. 3-GEMMASCOPE-RES-16K
    11. 5389
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and variables often used in equations and formulas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,
    -0.36
    <eos>
    -0.34
    र्ड
    -0.31
    Sort
    -0.30
     mình
    -0.30
     spy
    -0.30
     standard
    -0.29
     sort
    -0.29
     lit
    -0.28
    :)
    -0.28
    POSITIVE LOGITS
     '\\;'
    0.86
     cherchés
    0.83
     يتيمه
    0.80
     Meksiku
    0.80
     resourceCulture
    0.75
     wireType
    0.75
    httphttps
    0.74
    NameInMap
    0.73
     ModelExpression
    0.73
    setVerticalGroup
    0.71
    Activations Density 1.049%

    No Known Activations