© 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. 3190
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Pat" and variations thereof

    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
    +0.15
    0.9%
    663
    +0.15
    0.9%
    662
    +0.14
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    663
    +0.15
    0.03
    662
    +0.15
    0.02
    1142
    +0.14
    0.02
    Negative Logits
    <bos>
    -2.05
    
    -0.56
    //---
    -0.55
    rungsseite
    -0.54
     disbur
    -0.53
    /**
    -0.53
    setVerticalGroup
    -0.52
    ParallelGroup
    -0.52
    webElementXpaths
    -0.51
     endeavoured
    -0.51
    POSITIVE LOGITS
     Pat
    1.53
    Pat
    1.47
     pat
    1.36
    pat
    1.29
     PAT
    1.23
    PAT
    1.11
     Pats
    1.05
     pats
    0.98
     Patro
    0.97
    pats
    0.91
    Activations Density 0.036%

    No Known Activations