© 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. 100944
    Prev
    Next
    INDEX
    Explanations

    elements related to processes or actions involving physical manipulation or measurement

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

    Technical terms representing specific operations, components, or functions within specialized domains of knowledge.

    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
     فريبيس
    -0.67
    IVEREF
    -0.57
     Cad
    -0.50
    brainly
    -0.47
     OFDb
    -0.46
     cad
    -0.46
    verwijspagina
    -0.45
    :✨
    -0.45
     Prow
    -0.45
     Accent
    -0.45
    POSITIVE LOGITS
    Instead
    0.48
     instead
    0.46
     zamiast
    0.46
    
    0.45
     plutôt
    0.45
    instead
    0.44
    Jîn
    0.43
     ministerio
    0.43
     istället
    0.43
     propOrder
    0.42
    Activations Density 0.320%

    No Known Activations