Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 12783
    Prev
    Next
    INDEX
    Explanations

    concepts related to diversity and social justice in academia

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

    Racial diversity/equality

    np_acts-logits-general · gemini-2.0-flash

    racial diversity and equality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    complexContent
    -0.65
    ւ
    -0.50
    LogFactory
    -0.48
     _$
    -0.46
    loped
    -0.46
     thọ
    -0.46
    Mediabestanden
    -0.45
    sizeCache
    -0.45
     utafitiHapana
    -0.44
    FontWeight
    -0.44
    POSITIVE LOGITS
     diversity
    1.84
     Diversity
    1.77
    Diversity
    1.70
    diversity
    1.59
     racial
    1.59
     racism
    1.44
     racially
    1.44
     equality
    1.42
     Racial
    1.39
     inclu
    1.34
    Activations Density 0.459%

    No Known Activations