© 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. 773
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    +0.10
    0.4%
    478
    +0.05
    0.2%
    1806
    +0.05
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1032
    +0.10
    0.03
    1903
    +0.05
    0.03
    725
    +0.05
    0.03
    Negative Logits
    <bos>
    -1.59
    ///**
    -0.77
    /***
    
    -0.76
    public
    -0.69
    /**
    
    -0.69
    <?
    
    -0.68
    }{||
    -0.67
    //
    -0.66
    /**
    -0.65
    interface
    -0.65
    POSITIVE LOGITS
     proud
    2.02
     lidl
    1.86
    proud
    1.83
     stockholm
    1.69
     maneu
    1.68
    Proud
    1.67
     Proud
    1.66
     eiffel
    1.64
     affor
    1.63
     ibiza
    1.62
    Activations Density 0.064%

    No Known Activations