© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 2565
    Prev
    Next
    INDEX
    Explanations

    discussions regarding the complex history of slavery, including ownership and trading dynamics among various racial groups

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

    slavery or selling people

    np_acts-logits-general · gemini-2.0-flash

    people sold into slavery

    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
     infallib
    -0.60
    횟
    -0.57
    Sitz
    -0.57
     thicken
    -0.57
    tät
    -0.56
     Schützen
    -0.56
     ModelExpression
    -0.56
     للمعارف
    -0.55
    mybatisplus
    -0.55
     vegetarians
    -0.55
    POSITIVE LOGITS
     slave
    1.14
     slavery
    1.04
    slave
    1.01
     slaves
    0.96
     Slave
    0.94
     Slavery
    0.92
    Slave
    0.90
     ensla
    0.87
     escla
    0.87
     enslaved
    0.85
    Activations Density 0.225%

    No Known Activations