© 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. 15210
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and structure, particularly in code snippets

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

    Punctuation and code delimiters

    np_acts-logits-general · gemini-2.0-flash

    code formatting tags and structure

    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
    apimachinery
    -0.97
    interopRequire
    -0.84
    SequentialGroup
    -0.82
    multer
    -0.82
    SuppressMessage
    -0.81
     makeStyles
    -0.79
    Personendaten
    -0.76
    findpost
    -0.75
     multer
    -0.74
     createStore
    -0.73
    POSITIVE LOGITS
     botanique
    0.54
    ())))
    0.54
    ())));
    0.52
    ])->
    0.52
    <eos>
    0.52
     tekem
    0.51
    
    0.50
    MathML
    0.50
     }$
    0.48
    ultati
    0.47
    Activations Density 0.095%

    No Known Activations