© 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. 1701
    Prev
    Next
    INDEX
    Explanations

    informal language and personal anecdotes

    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
    +0.22
    1.2%
    381
    +0.13
    0.7%
    1047
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1047
    +0.22
    0.07
    1637
    +0.13
    0.06
    58
    +0.12
    0.06
    Negative Logits
    <bos>
    -3.11
    /***
    -1.16
    ⓧ
    -0.87
    ///**
    -0.82
    /*!
    -0.75
    <?
    -0.71
    /*
    -0.71
    //*/
    -0.69
     /**
    -0.68
    /**
    -0.68
    POSITIVE LOGITS
     So
    1.15
    So
    1.07
     impra
    0.96
     véhic
    0.95
     maneu
    0.90
     hilux
    0.87
     chrysler
    0.86
     bosch
    0.86
     tupperware
    0.85
     sooooo
    0.85
    Activations Density 0.145%

    No Known Activations