© 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. 18-GEMMASCOPE-RES-16K
    11. 10008
    Prev
    Next
    INDEX
    Explanations

    technical terms and descriptions related to digital technologies and their applications in various industries

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

    equipment and machines

    np_acts-logits-general · gemini-2.0-flash

    physical equipment and devices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    脚注の使い方
    -0.73
     للاسماء
    -0.66
     FetchType
    -0.63
    invokeLater
    -0.63
     XHTML
    -0.60
     quelquefois
    -0.59
     habet
    -0.59
     úteis
    -0.59
     Polynesia
    -0.59
     Audiodateien
    -0.59
    POSITIVE LOGITS
     equipment
    1.13
     devices
    1.00
     instruments
    0.92
     machines
    0.89
     Equipment
    0.85
     portable
    0.85
    equipment
    0.83
     appliances
    0.82
     hardware
    0.81
     equipments
    0.81
    Activations Density 0.593%

    No Known Activations