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. 13015
    Prev
    Next
    INDEX
    Explanations

    references to historical figures and discussions about their impact on society

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

    Black people or Africa

    np_acts-logits-general · gemini-2.0-flash

    African identity and ethnicity

    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
     AUSTR
    -0.48
     osz
    -0.48
    AUSTR
    -0.47
     zlo
    -0.46
     Kild
    -0.44
     vall
    -0.41
     Doyle
    -0.41
     Hobbit
    -0.41
     australian
    -0.41
     Bouchard
    -0.40
    POSITIVE LOGITS
     African
    1.68
     Afro
    1.53
    African
    1.52
    🏾
    1.50
     afro
    1.45
     Afric
    1.45
     african
    1.41
     AFRICAN
    1.35
    🏿
    1.32
    african
    1.32
    Activations Density 0.592%

    No Known Activations