© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 7389
    Prev
    Next
    INDEX
    Explanations

    instances of the word "spread" and its variations, indicating references to dissemination or distribution

    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
    HandlerContext
    -0.48
    الدراسه
    -0.47
    PMailer
    -0.44
     للمعارف
    -0.43
     Cey
    -0.40
    ագրություններ
    -0.40
    sizeCache
    -0.39
     فريبيس
    -0.39
    baomidou
    -0.38
    Blon
    -0.38
    POSITIVE LOGITS
     spread
    4.41
     Spread
    4.00
    spread
    3.98
    Spread
    3.84
     spreads
    3.48
     spreading
    3.25
     Spreading
    2.97
    spreading
    2.88
     spreader
    2.38
    pread
    2.28
    Activations Density 0.083%

    No Known Activations