© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3601
    Prev
    Next
    INDEX
    Explanations

    special characters or symbols commonly used in programming code

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

    Text around the tilde (~) character

    np_acts-logits-general · gemini-2.0-flash

    numbers following special characters

    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
    )))));
    -0.62
    
    
    -0.58
    amik
    -0.57
    dymyr
    -0.55
    rodu
    -0.54
     obstante
    -0.54
     True
    -0.52
    esgue
    -0.52
    まま
    -0.52
     maxWidth
    -0.51
    POSITIVE LOGITS
    -~
    1.10
    @~
    0.99
    *~
    0.92
    SharedDtor
    0.88
    '~
    0.87
    .~
    0.85
    richTextPanel
    0.80
     Administrativna
    0.77
    *~*~
    0.75
    )~
    0.75
    Activations Density 0.302%

    No Known Activations