© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 3-GEMMASCOPE-RES-16K
    11. 1402
    Prev
    Next
    INDEX
    Explanations

    numeric data and associated structures

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -1.16
     MainAxisSize
    -1.09
     doubtnut
    -1.00
     InputDecoration
    -0.88
     MessageBoxIcon
    -0.88
     оригіналу
    -0.86
     onAnimation
    -0.85
    DotNetBar
    -0.83
     Paglinawan
    -0.81
    رشف
    -0.81
    POSITIVE LOGITS
     re
    0.55
     seg
    0.55
     L
    0.54
    si
    0.53
    ch
    0.52
    sch
    0.52
    gs
    0.52
    po
    0.51
    lis
    0.50
     P
    0.50
    Activations Density 0.334%

    No Known Activations