© 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. 105513
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to organizational structure, operations, and processes

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

    Domain-specific terminology or jargon that describes specialized concepts, processes, or functions within professional or technical contexts.

    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
    السكان
    -0.32
     clothes
    -0.29
     Ky
    -0.28
    ↵↵↵↵
    -0.27
     residents
    -0.26
     (!
    -0.25
     banned
    -0.25
     Clothes
    -0.25
     ban
    -0.24
     Chine
    -0.24
    POSITIVE LOGITS
    
    0.93
     kasarigan
    0.89
    SBATCH
    0.84
     Geſch
    0.83
     Infórmanos
    0.82
     MainAxisSize
    0.77
     ujednoznacz
    0.74
    Ecotoxicity
    0.74
     MessageBoxIcon
    0.74
    featureID
    0.72
    Activations Density 3.561%

    No Known Activations