© 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
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 2705
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to definitions and their interpretations

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

    legal and technical terminology related to definitions.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    impianto
    -0.44
    
    -0.40
    pray
    -0.40
    UpInside
    -0.39
     seasoning
    -0.37
     meman
    -0.35
    DispatchQueue
    -0.34
     mist
    -0.33
     Vordergrund
    -0.33
     draw
    -0.33
    POSITIVE LOGITS
     definition
    1.27
     definitions
    1.13
     Definition
    1.05
    definition
    1.00
     definição
    1.00
     définition
    0.98
     definición
    0.96
     Definitions
    0.93
    Definition
    0.89
    DEFINITION
    0.87
    Activations Density 0.354%

    No Known Activations