© 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. 1344
    Prev
    Next
    INDEX
    Explanations

    lists and resources for educational purposes

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

    Lists of things

    np_acts-logits-general · gemini-2.0-flash

    lists of top items

    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
    SharedDtor
    -0.79
    ValueStyle
    -0.72
     AssemblyCulture
    -0.62
    medriver
    -0.60
     chng
    -0.57
    SequentialGroup
    -0.56
     AssemblyProduct
    -0.55
    RUnlock
    -0.54
    setdefault
    -0.51
    internalType
    -0.50
    POSITIVE LOGITS
     Top
    0.90
    Top
    0.89
     top
    0.87
     best
    0.85
    Best
    0.80
     ways
    0.80
     Best
    0.80
     besten
    0.76
    best
    0.76
     reasons
    0.76
    Activations Density 0.227%

    No Known Activations