© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 1617
    Prev
    Next
    INDEX
    Explanations

    the word "while" and its variations

    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
    +0.34
    1.8%
    971
    +0.10
    0.6%
    1404
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    971
    +0.34
    0.05
    1404
    +0.10
    0.05
    90
    +0.10
    0.05
    Negative Logits
    <bos>
    -2.77
    /***
    -0.76
    ///**
    -0.74
    ⓧ
    -0.72
    //<
    -0.61
    <!--
    -0.61
    //}
    -0.58
    ///////////////
    -0.58
    //{
    -0.57
    public
    -0.57
    POSITIVE LOGITS
     increa
    1.47
     affor
    1.46
     accla
    1.46
     maneu
    1.43
     impra
    1.39
     alre
    1.32
     whil
    1.29
     inev
    1.29
     guarante
    1.27
     unlaw
    1.27
    Activations Density 0.066%

    No Known Activations