© 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. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 12328
    Prev
    Next
    INDEX
    Explanations

    mentions of the hijab and related cultural or religious practices

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1331
    +0.11
    0.3%
    406
    +0.09
    0.3%
    1842
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1331
    +0.11
    0.04
    1033
    +0.09
    0.02
    1882
    +0.09
    0.04
    Negative Logits
     jaya
    -1.09
     saha
    -1.06
     Minang
    -1.04
     Seni
    -1.00
     gend
    -0.97
     Karya
    -0.94
     affez
    -0.94
     gila
    -0.93
     kac
    -0.92
     teri
    -0.92
    POSITIVE LOGITS
     Islam
    0.63
     Muslims
    0.61
     Islamic
    0.57
     Layla
    0.55
     Mónica
    0.54
     AssemblyCulture
    0.53
     musul
    0.53
     mosque
    0.51
    endphp
    0.51
    Islam
    0.51
    Activations Density 0.239%

    No Known Activations