© 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. 16147
    Prev
    Next
    INDEX
    Explanations

    programming syntax related to variable assignment and data structures

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

    Code-like syntax within double curly braces

    np_acts-logits-general · gemini-2.0-flash

    code templating with `{{` and `}}`

    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
    脚注の使い方
    -0.74
     GlobalKey
    -0.69
    mybatisplus
    -0.68
    ChildScrollView
    -0.68
    MENAFN
    -0.67
    RegressionTest
    -0.67
     onCancelled
    -0.67
     photolibrary
    -0.66
     Reſ
    -0.65
     myſelf
    -0.65
    POSITIVE LOGITS
    if
    0.60
    Convert
    0.59
     Convert
    0.54
     round
    0.53
    round
    0.53
     convert
    0.53
    Formats
    0.52
     format
    0.52
    Utils
    0.50
     String
    0.50
    Activations Density 0.092%

    No Known Activations