© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 460
    Prev
    Next
    INDEX
    Explanations

    keywords related to racial identities and social justice issues

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

    references to racial and ethnic groups, particularly terms describing Black, White, Hispanic, Asian, Native American, and other demographic communities.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pulseira
    -0.45
     okazji
    -0.36
    convite
    -0.35
     sprend
    -0.33
    transitions
    -0.33
     konkurs
    -0.33
    setViewportView
    -0.33
    brinco
    -0.32
     tindak
    -0.32
     revés
    -0.31
    POSITIVE LOGITS
     peoples
    0.67
     disambiguazione
    0.65
     surla
    0.65
    ValueStyle
    0.63
     communities
    0.63
     ब्रेकडाउन
    0.63
     woman
    0.62
     suprema
    0.61
     youths
    0.59
     befolk
    0.59
    Activations Density 0.365%

    No Known Activations