© 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. 967
    Prev
    Next
    INDEX
    Explanations

    phrases related to reporting incidents to authorities or seeking help, particularly in the context of crime, harassment, or safety concerns.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    information regarding legal issues or cases.

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

    descriptions of physical attributes and information about individuals.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    Reporting an incident or problem

    np_acts-logits-general · gemini-2.0-flash

    reporting issues or complaints

    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
     ujednoznacz
    -0.68
    InSection
    -0.67
    RegressionTest
    -0.66
    saraba
    -0.60
    AsUp
    -0.59
     CreateTagHelper
    -0.59
     विश्वसनीयता
    -0.58
    帖最后由
    -0.57
    !*\
    -0.55
     calendriers
    -0.55
    POSITIVE LOGITS
     reporting
    2.25
     report
    2.19
     reported
    2.05
     Report
    1.98
     Reporting
    1.97
    Report
    1.97
    report
    1.96
     reports
    1.93
     REPORT
    1.88
    REPORT
    1.87
    Activations Density 0.344%

    No Known Activations