© 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. 2787
    Prev
    Next
    INDEX
    Explanations

    elements related to transactions and exchanges, particularly involving money

    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
    1150
    +0.25
    1.1%
    50
    +0.23
    1.0%
    382
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.25
    0.09
    1150
    +0.23
    0.05
    2019
    +0.12
    0.09
    Negative Logits
    <bos>
    -3.20
    ⓧ
    -1.24
    
    -1.15
    /***
    -1.12
    /**
    -1.02
    /*!
    -0.95
    <?
    -0.85
    #![
    -0.80
    endwhile
    -0.80
    /*
    -0.75
    POSITIVE LOGITS
     Considerable
    0.66
     unfore
    0.64
     disreg
    0.62
     topographical
    0.61
     belliger
    0.60
     nutritive
    0.59
     Pyrene
    0.59
     Byp
    0.58
     confiscation
    0.57
     Alfalfa
    0.57
    Activations Density 0.854%

    No Known Activations