© 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. 4-GEMMASCOPE-RES-16K
    11. 16341
    Prev
    Next
    INDEX
    Explanations

    conjunctions and transitional phrases indicating contrast or comparison

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     g
    -0.54
     basis
    -0.49
     bak
    -0.48
     Anda
    -0.48
     right
    -0.48
     gy
    -0.47
     bel
    -0.46
     bal
    -0.46
     working
    -0.45
     b
    -0.45
    POSITIVE LOGITS
    albeit
    1.36
     Meski
    1.30
     though
    1.28
    though
    1.28
     THOUGH
    1.28
     albeit
    1.25
    Meski
    1.24
     Zwar
    1.23
     although
    1.18
    although
    1.18
    Activations Density 0.355%

    No Known Activations