© 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-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104951
    Prev
    Next
    INDEX
    Explanations

    technical jargon and specific terminology related to digital technology and programming

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Programming symbols, technical abbreviations, and specialized terminology that appear in code snippets, scientific documentation, and technical discussions.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219
    Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    archiviato
    -0.52
    Personendaten
    -0.50
    ValueStyle
    -0.48
    Geplaatst
    -0.45
    Obrázky
    -0.45
     bezeichneter
    -0.44
    OptionsMenu
    -0.44
     protoimpl
    -0.42
     समीक्षाओं
    -0.42
    semester
    -0.41
    POSITIVE LOGITS
     AssemblyCulture
    0.48
    Kjelder
    0.43
    دانشنامهٔ
    0.42
    Földrajzportál
    0.40
    ->___
    0.40
     ControllerBase
    0.40
     BULLETIN
    0.37
     MonoBehaviour
    0.36
     somebody
    0.36
    OpenHelper
    0.36
    Activations Density 0.210%

    No Known Activations