© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 13107
    Prev
    Next
    INDEX
    Explanations

    terms that indicate cultural integration and affiliation

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

    words related to cultural identity, assimilation, and acculturation processes.

    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
    CONSIN
    -0.39
    Życiorys
    -0.38
    FieldNumber
    -0.37
     صح
    -0.36
    SeekBar
    -0.36
     Corse
    -0.35
     leaderboard
    -0.35
    昏
    -0.35
    SuspendLayout
    -0.35
     strateg
    -0.35
    POSITIVE LOGITS
     culture
    2.44
     cultural
    2.27
     cultures
    2.22
    culture
    2.11
     Culture
    2.02
    Culture
    1.95
    cultural
    1.95
     CULTURE
    1.93
     cultura
    1.91
     Cultural
    1.88
    Activations Density 0.352%

    No Known Activations