© 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. 24-GEMMASCOPE-RES-16K
    11. 14582
    Prev
    Next
    INDEX
    Explanations

    references to demographics associated with diversity and discrimination

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

    inclusivity or variety

    np_acts-logits-general · gemini-2.0-flash

    all genders, races, ages, and backgrounds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     برانيه
    -0.63
    SerializedSize
    -0.59
     estekak
    -0.58
    ngdoc
    -0.56
    Ligações
    -0.56
     eventdata
    -0.55
    ProgressHUD
    -0.54
    órmulas
    -0.53
    InjectMocks
    -0.50
    addSubview
    -0.48
    POSITIVE LOGITS
     race
    1.31
     ethnicity
    1.28
     nationality
    1.22
     background
    1.16
     gender
    1.11
     religion
    1.09
     backgrounds
    1.04
    race
    1.02
     age
    1.01
     creed
    0.97
    Activations Density 0.447%

    No Known Activations