© 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. 3-GEMMASCOPE-RES-16K
    11. 4379
    Prev
    Next
    INDEX
    Explanations

    phrases related to methods and processes in scientific or technical contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    AnimationsModule
    -0.86
     समीक्षक
    -0.83
     purpoſe
    -0.80
    JspWriter
    -0.80
     发表于
    -0.78
     myſelf
    -0.77
     ſever
    -0.76
    rawDesc
    -0.75
     Majefty
    -0.75
    setVerticalGroup
    -0.74
    POSITIVE LOGITS
     through
    1.10
     mediante
    1.09
    Through
    1.08
     Through
    1.02
     pomocí
    1.02
    through
    1.00
     tramite
    0.98
     mittels
    0.91
     using
    0.91
     באמצעות
    0.89
    Activations Density 0.420%

    No Known Activations