© 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. 3423
    Prev
    Next
    INDEX
    Explanations

    references to scripture and religious texts

    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
    50
    +0.19
    0.7%
    1741
    +0.12
    0.5%
    453
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1202
    +0.19
    0.01
    1191
    +0.12
    0.01
    1429
    +0.10
    0.02
    Negative Logits
    <bos>
    -1.67
    /**
    -1.43
    ⓧ
    -1.35
    <?
    -1.29
    
    -1.26
    /*
    -1.09
    <?
    -1.08
    Transcripción
    -0.77
    <>
    -0.74
    /*!
    -0.73
    POSITIVE LOGITS
     lele
    1.24
     marte
    1.09
     toul
    1.05
     ananas
    1.05
     fei
    0.99
     cæ
    0.98
     balon
    0.97
     gmbh
    0.97
     krab
    0.96
     nomine
    0.96
    Activations Density 0.028%

    No Known Activations