© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 3082
    Prev
    Next
    INDEX
    Explanations

    specific components and modifications related to motorcycle performance and design

    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
    +0.23
    1.0%
    1385
    +0.21
    0.9%
    876
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.23
    0.09
    876
    +0.21
    -0.01
    1842
    +0.11
    0.03
    Negative Logits
    <bos>
    -2.88
    ⓧ
    -1.13
    <?
    -1.13
    /**
    -1.08
    /***
    -1.07
    
    -1.05
    <?
    -0.89
    ///**
    -0.88
    {?>
    -0.82
    /*
    -0.81
    POSITIVE LOGITS
     malheureux
    1.06
     wikihow
    1.03
     malheure
    0.97
     effray
    0.95
     ItemType
    0.94
     unsplash
    0.93
     conftest
    0.88
     🔥🔥
    0.87
     docx
    0.86
     embodi
    0.85
    Activations Density 0.301%

    No Known Activations