© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 3375
    Prev
    Next
    INDEX
    Explanations

    elements related to family dynamics and interfaith relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    垂
    -0.44
    InSection
    -0.41
     mola
    -0.38
     CASO
    -0.38
     raga
    -0.38
     չ
    -0.36
     fang
    -0.36
     vain
    -0.36
    mola
    -0.36
     propOrder
    -0.35
    POSITIVE LOGITS
     husband
    0.73
     wife
    0.68
     spouse
    0.66
    Husband
    0.66
     spouses
    0.65
     Wife
    0.63
     Husband
    0.63
     parejas
    0.62
     suami
    0.62
     pasangan
    0.60
    Activations Density 0.456%

    No Known Activations