© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 2311
    Prev
    Next
    INDEX
    Explanations

    references to the word "surface" mentioned with varying relevance in scientific contexts

    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.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.18
    1.1%
    1870
    +0.12
    0.7%
    577
    +0.09
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1602
    +0.18
    0.02
    1133
    +0.12
    0.02
    1385
    +0.09
    0.02
    Negative Logits
    <bos>
    -3.21
    ⓧ
    -1.10
    <?
    -1.02
    
    -1.01
    /**
    -0.95
    /*
    -0.92
    /***
    -0.80
    <?
    -0.78
    #![
    -0.73
    ///**
    -0.72
    POSITIVE LOGITS
     lele
    1.46
     bandung
    1.34
     meis
    1.26
     jaya
    1.23
     wien
    1.21
     Surface
    1.18
     maroc
    1.17
     kase
    1.17
     levis
    1.16
     fua
    1.15
    Activations Density 0.057%

    No Known Activations