© 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 - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 9702
    Prev
    Next
    INDEX
    Explanations

    references to legal frameworks and protections against discrimination and harassment

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

    "Discrimination" or "harassment"

    np_acts-logits-general · gemini-2.0-flash

    sex discrimination harassment

    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
    ImageContext
    -0.55
    出版年
    -0.50
    fromnode
    -0.50
    )||
    -0.46
     ko
    -0.44
    省市镇
    -0.44
     '').
    -0.44
     canh
    -0.43
    ито
    -0.43
    Carriera
    -0.43
    POSITIVE LOGITS
     discrimination
    1.04
     Discrimination
    1.01
     EconPapers
    0.94
     discriminated
    0.90
    discrimination
    0.88
     Equal
    0.86
     Harassment
    0.82
     discriminatory
    0.80
     Discrimin
    0.78
     disability
    0.78
    Activations Density 0.586%

    No Known Activations