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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 124113
    Prev
    Next
    INDEX
    Explanations

    terms related to communication protocols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    protocols determining

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
    Not in Any Lists

    No Comments

    Negative Logits
     cinquante
    -0.48
     varones
    -0.46
     Herramientas
    -0.45
     âgé
    -0.45
     franceses
    -0.45
     augmenté
    -0.45
     férias
    -0.45
     alemanes
    -0.44
     neuve
    -0.43
     réelle
    -0.43
    POSITIVE LOGITS
     protocol
    1.32
     Protocol
    1.30
     PROTOCOL
    1.26
    Protocol
    1.24
    protocol
    1.20
     protocols
    1.20
     Protocols
    1.11
    PROTOCOL
    1.09
    protocols
    1.01
    Protocols
    0.94
    Activations Density 0.010%

    No Known Activations