© 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. 7780
    Prev
    Next
    INDEX
    Explanations

    addresses and contact information such as phone numbers and emails

    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
    1978
    +0.12
    0.6%
    50
    +0.11
    0.5%
    1870
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1978
    +0.12
    0.12
    1527
    +0.11
    0.08
    609
    +0.10
    0.08
    Negative Logits
    <bos>
    -2.62
    /***
    -1.01
    ///**
    -0.80
    /**
    -0.73
    ⓧ
    -0.72
    
    -0.72
    <!--
    -0.69
    /*!
    -0.68
    //};
    -0.67
    <?
    -0.67
    POSITIVE LOGITS
     maneu
    1.57
     affor
    1.51
     disreg
    1.39
     increa
    1.38
     impra
    1.34
     suscep
    1.31
     reluct
    1.20
     resear
    1.19
     strick
    1.19
     stockholm
    1.18
    Activations Density 0.418%

    No Known Activations