© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 4446
    Prev
    Next
    INDEX
    Explanations

    configuration-related terms and elements in code or scripts

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

    Code configurations and settings

    np_acts-logits-general · gemini-2.0-flash

    config

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     ostavi
    -0.61
    ellido
    -0.54
     Herd
    -0.49
     Motta
    -0.47
     Perr
    -0.47
     acteurs
    -0.46
     Stearns
    -0.46
    nader
    -0.45
     przys
    -0.45
     cutters
    -0.45
    POSITIVE LOGITS
     config
    2.56
    config
    2.38
     configuration
    2.37
     Config
    2.35
     Configuration
    2.24
    Config
    2.23
    CONFIG
    2.06
    Configuration
    2.05
     configurations
    2.03
     configs
    2.02
    Activations Density 0.160%

    No Known Activations