© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 9400
    Prev
    Next
    INDEX
    Explanations

    phrases that define or describe mathematical relationships and conditions

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ↵↵
    -0.42
     once
    -0.39
    sev
    -0.39
    Once
    -0.38
     Once
    -0.36
     No
    -0.35
     pais
    -0.35
    oles
    -0.35
    انه
    -0.35
     Don
    -0.34
    POSITIVE LOGITS
    makeConstraints
    1.08
     Roskov
    1.03
     مشين
    1.01
     &___
    1.00
    =$?
    0.94
    MLLoader
    0.93
     Савезне
    0.91
    tagHelperRunner
    0.91
     autorytatywna
    0.89
     שוליים
    0.88
    Activations Density 0.906%

    No Known Activations