© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 1464
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to protection and safeguarding

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

    topics related to protection and professionalism in the workplace, especially concerning women and their rights

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

    protect against

    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
    RegressionTest
    -0.94
     cherchés
    -0.87
     ComVisible
    -0.72
    Архівовано
    -0.69
    ukone
    -0.67
     autorytatywna
    -0.67
     للاسماء
    -0.64
    Jîn
    -0.64
    省市镇
    -0.64
    ="@+
    -0.63
    POSITIVE LOGITS
     against
    1.14
    against
    1.03
     Against
    0.99
    Against
    0.91
     rights
    0.79
     integrity
    0.79
     interests
    0.77
     AGAINST
    0.71
     from
    0.71
     vulnerable
    0.69
    Activations Density 0.057%

    No Known Activations