© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 110
    Prev
    Next
    INDEX
    Explanations

    phrases related to permissions, religious beliefs, and genealogy

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.13
    0.9%
    429
    +0.03
    0.2%
    1302
    +0.02
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1671
    +0.13
    0.07
    680
    +0.03
    0.07
    1137
    +0.02
    0.09
    Negative Logits
    <bos>
    -2.34
    /***
    
    -0.97
    
    
    -0.91
    ⓧ
    -0.90
    <?
    -0.78
    /**
    -0.77
    <?
    
    -0.76
    public
    -0.75
    /*
    -0.75
    ///**
    -0.72
    POSITIVE LOGITS
     stockholm
    1.78
     lidl
    1.63
     affor
    1.62
     wien
    1.62
     maneu
    1.61
     maroc
    1.54
     meis
    1.50
     accla
    1.48
     aen
    1.47
     ibiza
    1.46
    Activations Density 2.404%

    No Known Activations