© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 15347
    Prev
    Next
    INDEX
    Explanations

    concepts and discussions around fairness

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

    "fair"

    np_acts-logits-general · gemini-2.0-flash

    fairness and justice

    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
     propOrder
    -1.15
     насељу
    -0.99
     يتيمه
    -0.92
    oredCriteria
    -0.91
    engin
    -0.83
    GoogleApiClient
    -0.82
     FetchType
    -0.81
     виправивши
    -0.80
    rmtree
    -0.80
     estimés
    -0.79
    POSITIVE LOGITS
    fair
    1.40
     Fair
    1.39
    Fair
    1.39
    FAIR
    1.33
     FAIR
    1.30
     fair
    1.25
     Fairness
    0.97
     fairness
    0.95
     fairer
    0.93
     fairs
    0.92
    Activations Density 0.086%

    No Known Activations