© 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. 0-RES-JB
    11. 1909
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "the", showing a varying strength of activation

    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
    +0.22
    1.8%
    2019
    +0.10
    0.8%
    1325
    +0.03
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1042
    +0.22
    0.19
    1967
    +0.10
    -0.02
    1407
    +0.03
    0.16
    Negative Logits
    <bos>
    -3.47
    ⓧ
    -1.11
    /**
    -1.09
    
    -1.08
    <?
    -1.05
    /*
    -1.00
    /*++
    -0.83
    #
    -0.82
    <?
    -0.82
    ///**
    -0.80
    POSITIVE LOGITS
     maneu
    2.33
     affor
    2.10
     increa
    2.05
     accla
    2.05
     impra
    2.04
     reluct
    1.95
     disagre
    1.91
     stockholm
    1.90
     emphat
    1.90
     depic
    1.89
    Activations Density 3.101%

    No Known Activations