© 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. 15782
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and technical specifications

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

    Fractions or division operations

    np_acts-logits-general · gemini-2.0-flash

    numbers, units, and fractions

    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
     ppl
    -0.70
     např
    -0.62
     Esau
    -0.59
    FWIW
    -0.56
     govt
    -0.55
     чел
    -0.54
     ČR
    -0.54
     Asst
    -0.52
     Hwy
    -0.52
     Univ
    -0.52
    POSITIVE LOGITS
     minus
    0.98
    etera
    0.98
     plus
    0.83
     fifty
    0.76
    minus
    0.76
    ousand
    0.75
    viewDidLoad
    0.75
     nineteen
    0.74
     ninety
    0.74
     seventy
    0.73
    Activations Density 0.949%

    No Known Activations