© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 6357
    Prev
    Next
    INDEX
    Explanations

    notifications or alerts posted within a website or platform

    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
    +0.20
    1.1%
    1677
    +0.09
    0.5%
    1008
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1008
    +0.20
    0.05
    1861
    +0.09
    0.05
    1677
    +0.09
    0.04
    Negative Logits
    <bos>
    -3.15
    ⓧ
    -1.17
    <?
    -1.05
    /**
    -1.01
    /*
    -0.85
    /*!
    -0.84
    
    -0.80
    /***
    -0.79
     springfox
    -0.75
    ///**
    -0.74
    POSITIVE LOGITS
     maneu
    1.87
     increa
    1.81
     affor
    1.80
     impra
    1.77
     lele
    1.73
     bandung
    1.73
     stockholm
    1.72
     strick
    1.67
     wien
    1.65
     unspeak
    1.63
    Activations Density 0.161%

    No Known Activations