© 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. 1662
    Prev
    Next
    INDEX
    Explanations

    expressions of conflict and resistance in dialogue

    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
    +0.24
    1.0%
    906
    +0.13
    0.5%
    394
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    319
    +0.24
    0.04
    381
    +0.13
    0.03
    1419
    +0.13
    0.04
    Negative Logits
    <bos>
    -1.98
    ⓧ
    -0.97
    <?
    -0.91
    <?
    -0.82
    /***
    -0.76
    
    -0.73
    ///**
    -0.69
    /**
    -0.68
    /*
    -0.68
    bewerken
    -0.66
    POSITIVE LOGITS
     unlaw
    1.01
     tupperware
    0.95
     shenan
    0.94
     affor
    0.93
     hairc
    0.91
     ingrat
    0.82
     reluct
    0.81
     pollut
    0.81
     ecru
    0.81
     maneu
    0.81
    Activations Density 0.258%

    No Known Activations