© 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. 1436
    Prev
    Next
    INDEX
    Explanations

    quotation marks in a dialogue context

    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
    +0.28
    1.4%
    2019
    +0.19
    1.0%
    381
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    878
    +0.28
    0.07
    605
    +0.19
    0.04
    270
    +0.15
    0.05
    Negative Logits
    <bos>
    -3.05
    ⓧ
    -1.08
    <?
    -0.95
    
    -0.87
    /**
    -0.86
    /*
    -0.76
    /***
    -0.76
    EndProject
    -0.73
    ///**
    -0.71
    EndGlobalSection
    -0.69
    POSITIVE LOGITS
     seksi
    1.04
     maroc
    1.03
     kafe
    0.96
     cartier
    0.96
     bandung
    0.96
     jaya
    0.94
     moza
    0.93
     jawa
    0.92
     ados
    0.92
     aveug
    0.89
    Activations Density 0.108%

    No Known Activations