© 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. 16-GEMMASCOPE-RES-16K
    11. 9300
    Prev
    Next
    INDEX
    Explanations

    references to race or ethnicity in relation to socioeconomic conditions

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

    Entitlements, promises, or compensation

    np_acts-logits-general · gemini-2.0-flash

    promised compensation and entitlements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.79
    Diwedd
    -0.73
     nakalista
    -0.67
     MaterialApp
    -0.63
     pinulongan
    -0.63
    ⓧ
    -0.63
    RegistryLite
    -0.62
     AssemblyTitle
    -0.61
     مشين
    -0.58
    adaptiveStyles
    -0.58
    POSITIVE LOGITS
     promised
    0.75
     compensation
    0.61
     diperhatikan
    0.60
    clusão
    0.57
     regalías
    0.55
     entitlements
    0.55
     guarantees
    0.55
     guaranteed
    0.54
     equalization
    0.54
     berücksichtigt
    0.54
    Activations Density 0.350%

    No Known Activations