© 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. 444
    Prev
    Next
    INDEX
    Explanations

    tips and advice related to etiquette and proper conduct in social situations

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

    Advice, warnings, or rules

    np_acts-logits-general · gemini-2.0-flash

    rules and advice

    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
     المعيارى
    -0.93
    tagHelperRunner
    -0.88
    RectangleBorder
    -0.88
     GenerationType
    -0.80
    XmlAccessType
    -0.77
     незавершена
    -0.75
    GEBURTSDATUM
    -0.74
    TemporalType
    -0.71
    OGND
    -0.71
    下载附件
    -0.68
    POSITIVE LOGITS
     always
    1.55
     Always
    1.50
    Always
    1.47
     never
    1.33
    always
    1.27
    ALWAYS
    1.26
     ALWAYS
    1.22
     Never
    1.22
    Never
    1.20
     Avoid
    1.17
    Activations Density 0.296%

    No Known Activations