© 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-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 7974
    Prev
    Next
    INDEX
    Explanations

    financial figures and currencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 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
    e
    -0.63
     Mancini
    -0.57
    y
    -0.55
    NameInMap
    -0.55
    scrollTop
    -0.52
    P
    -0.51
    Sy
    -0.51
     kim
    -0.50
    moveToFirst
    -0.50
    R
    -0.50
    POSITIVE LOGITS
     USD
    2.19
    USD
    2.02
    usd
    1.48
     usd
    1.38
     EUR
    1.37
    EUR
    1.19
     GBP
    1.10
     SGD
    0.94
    GBP
    0.88
    ագրություններ
    0.87
    Activations Density 0.089%

    No Known Activations