© 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. 22-GEMMASCOPE-RES-16K
    11. 11573
    Prev
    Next
    INDEX
    Explanations

    numerical data and references related to statistics or measurements

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

    Numbers followed by units of measurement

    np_acts-logits-general · gemini-2.0-flash

    numbers followed by units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MENAFN
    -1.09
    脚注の使い方
    -1.06
     فريبيس
    -0.96
    verwijspagina
    -0.85
     EconPapers
    -0.82
    abestanden
    -0.77
    ſelves
    -0.75
    parsedMessage
    -0.75
     itſelf
    -0.75
    homonymie
    -0.74
    POSITIVE LOGITS
    ¼
    0.65
     potuto
    0.57
    ½
    0.57
     daß
    0.52
    Ditto
    0.49
     phẩm
    0.48
     dovuto
    0.45
    shadowOffset
    0.45
    ¾
    0.44
    Told
    0.44
    Activations Density 0.508%

    No Known Activations