© 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. 16291
    Prev
    Next
    INDEX
    Explanations

    structural components and mathematical notations in complex documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    antism
    -0.56
    LOAT
    -0.54
    (&:
    -0.52
     inoxydable
    -0.51
     bezeichneter
    -0.50
    NullException
    -0.49
     judiciaire
    -0.48
    CMP
    -0.47
    otomy
    -0.45
    ériale
    -0.45
    POSITIVE LOGITS
     ModelExpression
    0.80
     nahilalakip
    0.69
    principalTable
    0.61
    новништво
    0.59
     '&#
    0.58
    ürn
    0.58
    Posted
    0.57
    stdafx
    0.56
    Gön
    0.56
    новниш
    0.55
    Activations Density 1.312%

    No Known Activations