© 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. 5828
    Prev
    Next
    INDEX
    Explanations

    references to political events and community initiatives

    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
    +0.32
    1.4%
    381
    +0.09
    0.4%
    2019
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1937
    +0.32
    0.08
    289
    +0.09
    0.06
    513
    +0.09
    0.06
    Negative Logits
    <bos>
    -3.05
     /**
    -0.64
     their
    -0.64
    <?
    -0.62
    ///**
    -0.62
     these
    -0.62
    /***
    -0.61
    public
    -0.61
     his
    -0.60
    this
    -0.60
    POSITIVE LOGITS
     accla
    1.49
     affor
    1.48
     lidl
    1.42
     maneu
    1.36
     impra
    1.33
     excru
    1.30
     stockholm
    1.30
     increa
    1.29
     sovere
    1.28
     unden
    1.27
    Activations Density 2.450%

    No Known Activations