© 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. 12-GEMMASCOPE-RES-16K
    11. 227
    Prev
    Next
    INDEX
    Explanations

    references to digital tools or platforms related to information and data management

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

    technical terms and phrases related to drug metabolism and pharmacokinetics in pharmaceutical research

    oai_token-act-pair · gpt-5-nanoTriggered by @phuongpham0213
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pliny
    -0.44
    هی
    -0.43
    tableFuture
    -0.43
     Puig
    -0.42
     hist
    -0.42
    pidou
    -0.41
     prossimo
    -0.41
    Ад
    -0.41
    がら
    -0.40
     interesan
    -0.38
    POSITIVE LOGITS
     surla
    0.81
    帖最后由
    0.75
     autorytatywna
    0.74
     nakalista
    0.70
     <>",
    0.69
    windowFixed
    0.68
    الإنجليزية
    0.67
    исленность
    0.66
    ͟
    0.62
    parsedMessage
    0.62
    Activations Density 0.411%

    No Known Activations