© 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. 3539
    Prev
    Next
    INDEX
    Explanations

    numerical values or data points within a dataset or text

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

    Numbers with multiple digits

    np_acts-logits-general · gemini-2.0-flash

    numbers and identifiers

    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
    enderror
    -0.88
     الرياضيه
    -0.84
    horabuena
    -0.83
     myſelf
    -0.82
     Efq
    -0.81
     AssemblyCompany
    -0.79
     Monfieur
    -0.76
     pleaſure
    -0.75
     betweenstory
    -0.72
     Jefus
    -0.70
    POSITIVE LOGITS
    umia
    0.52
     North
    0.49
    baud
    0.49
     Main
    0.49
    igra
    0.46
     votes
    0.46
     Ober
    0.46
    巷
    0.46
    cip
    0.45
    PREFERRED
    0.45
    Activations Density 0.646%

    No Known Activations