© 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. 11361
    Prev
    Next
    INDEX
    Explanations

    words indicating warnings or notices about potential issues or alerts

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

    caution or attention

    np_acts-logits-general · gemini-2.0-flash

    warnings and notices

    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
     صوتيه
    -0.94
     FetchType
    -0.75
     CreateTagHelper
    -0.71
     استنادى
    -0.69
     المعيارى
    -0.65
     aDecoder
    -0.62
    Izvori
    -0.61
    okhttp
    -0.60
    hdashline
    -0.60
    ServletRequest
    -0.59
    POSITIVE LOGITS
     alerts
    0.80
    astify
    0.78
     alert
    0.75
     WARN
    0.74
     warning
    0.71
     Warnings
    0.69
     notices
    0.68
     Alerts
    0.67
     warnings
    0.67
    Alerts
    0.66
    Activations Density 0.190%

    No Known Activations