© 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. 1435
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of people

    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
    +0.31
    1.3%
    184
    +0.10
    0.4%
    1741
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.31
    0.14
    1097
    +0.10
    0.12
    1650
    +0.10
    0.06
    Negative Logits
    <bos>
    -2.67
    /***
    -0.97
    ///**
    -0.90
    EndGlobalSection
    -0.84
    /*!
    -0.82
    Autoritní
    -0.81
     /**
    -0.78
    !*\
    -0.74
    脚注の使い方
    -0.73
     fono
    -0.73
    POSITIVE LOGITS
     maneu
    1.64
     reluct
    1.58
     unspeak
    1.55
     shenan
    1.55
     impra
    1.54
     disagre
    1.47
     resear
    1.47
     increa
    1.46
     accla
    1.45
     affor
    1.43
    Activations Density 0.262%

    No Known Activations