© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 1628
    Prev
    Next
    INDEX
    Explanations

    advice and guidance related to personal struggles, particularly for women

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

    advice directed at women dealing with emotional challenges, particularly related to pregnancy and relationships

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

    advice and warnings

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    Personendaten
    -0.86
    /**
    -0.70
    Часть
    -0.66
     autorytatywna
    -0.60
     thiệu
    -0.59
    GOTREF
    -0.59
    RectangleBorder
    -0.59
    explique
    -0.58
    expandindo
    -0.58
    $.
    
    -0.57
    POSITIVE LOGITS
     advice
    0.86
    Advice
    0.84
    advice
    0.79
     Advice
    0.73
     Beware
    0.72
     ADVICE
    0.70
     always
    0.69
    Always
    0.69
     Always
    0.68
     beware
    0.66
    Activations Density 0.064%

    No Known Activations