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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 3520
    Prev
    Next
    INDEX
    Explanations

    references to the religion of Jehovah's Witnesses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1178
    +0.18
    0.9%
    1187
    +0.14
    0.7%
    1575
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1575
    +0.18
    0.03
    227
    +0.14
    0.04
    1741
    +0.14
    0.01
    Negative Logits
     iyon
    -0.83
     kasama
    -0.70
     guma
    -0.69
     Palembang
    -0.67
     Bekasi
    -0.65
     meri
    -0.64
     kani
    -0.62
     felicity
    -0.61
     susun
    -0.60
     Chaves
    -0.59
    POSITIVE LOGITS
     Jehovah
    1.15
    Jeho
    1.01
    seigneur
    0.85
     pantal
    0.81
     chèvre
    0.81
     lapin
    0.79
     chevalier
    0.78
     bapt
    0.76
    sieur
    0.74
    렷
    0.74
    Activations Density 0.177%

    No Known Activations