© 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
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 7124
    Prev
    Next
    INDEX
    Explanations

    legal and technical text related to contracts, liabilities, and confidentiality

    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
    +0.26
    1.2%
    990
    +0.10
    0.4%
    812
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    990
    +0.26
    0.03
    44
    +0.10
    0.02
    179
    +0.09
    0.02
    Negative Logits
    <bos>
    -3.47
    
    -0.84
    <?
    -0.74
    ///**
    -0.74
    /*
    -0.71
    /***
    -0.70
    ोंने
    -0.70
    ⓧ
    -0.69
    //
    -0.64
    /**
    -0.64
    POSITIVE LOGITS
     affor
    1.52
     maneu
    1.46
     lidl
    1.38
     reluct
    1.36
     impra
    1.35
     strick
    1.32
     excru
    1.31
     disagre
    1.31
     unlaw
    1.31
     exorbit
    1.31
    Activations Density 0.063%

    No Known Activations