© 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. 21-GEMMASCOPE-RES-16K
    11. 9007
    Prev
    Next
    INDEX
    Explanations

    terms related to discrimination and diversity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     receptor
    -0.84
     Receptor
    -0.82
    Research
    -0.81
     Research
    -0.80
    Restaurant
    -0.79
     raced
    -0.78
     RESEARCH
    -0.78
     redness
    -0.77
     Restaurant
    -0.77
     resistor
    -0.77
    POSITIVE LOGITS
    ContentAsync
    0.54
    lgari
    0.45
    =============
    0.41
    ============
    0.40
    inguished
    0.40
    IsContent
    0.38
     مشين
    0.38
    Kval
    0.38
    لمين
    0.37
    HomeAsUpEnabled
    0.37
    Activations Density 0.433%

    No Known Activations