© 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. 38-GEMMASCOPE-RES-16K
    11. 7701
    Prev
    Next
    INDEX
    Explanations

    references to religious and community aspects related to marriage, choices, and the implications of such decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uxxxx
    -0.99
    httphttps
    -0.92
    tagHelperRunner
    -0.90
    expandindo
    -0.81
    IUrlHelper
    -0.79
    تقاوى
    -0.79
     للاسماء
    -0.77
     يتيمه
    -0.77
     disambiguazione
    -0.74
    errHandler
    -0.73
    POSITIVE LOGITS
     hinweg
    0.54
     alike
    0.53
     etc
    0.50
    surate
    0.44
    持
    0.43
     Edition
    0.41
     purposes
    0.41
    inguishing
    0.40
    )
    0.40
    来说
    0.39
    Activations Density 3.267%

    No Known Activations