© 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. 1638
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names of political figures

    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
    +0.13
    0.5%
    1150
    +0.10
    0.4%
    1741
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1097
    +0.13
    0.07
    2043
    +0.10
    0.06
    1364
    +0.09
    0.05
    Negative Logits
    <bos>
    -2.65
    /***
    -1.02
    ⓧ
    -0.98
    <?
    -0.85
    ///**
    -0.82
    //*/
    -0.71
    //});
    -0.70
    //};
    -0.65
    
    -0.63
    <?
    -0.63
    POSITIVE LOGITS
     kasa
    1.16
     saha
    1.06
     jawa
    1.03
     kac
    1.01
     kesi
    0.99
     lele
    0.99
     saar
    0.96
     saba
    0.94
     kaos
    0.94
     seksi
    0.93
    Activations Density 0.174%

    No Known Activations