© 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. 7117
    Prev
    Next
    INDEX
    Explanations

    currency symbols and financial metrics in the text

    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
     Paglinawan
    -0.75
     Geiſt
    -0.65
    AssignableFrom
    -0.63
     ویکی‌پدی
    -0.63
    |}{$
    -0.61
    HomeAsUpEnabled
    -0.61
     Normdatei
    -0.60
     $_(
    -0.59
    〬
    -0.58
    $
    -0.57
    POSITIVE LOGITS
    twimg
    0.33
    ględ
    0.26
    webElementGuid
    0.26
    
    0.24
    arakat
    0.22
     @"/
    0.22
    ----</
    0.21
     esper
    0.20
     kea
    0.20
     زد
    0.20
    Activations Density 1.128%

    No Known Activations