© 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. 1225
    Prev
    Next
    INDEX
    Explanations

    names of political figures and locations

    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
    +0.36
    2.3%
    1741
    +0.20
    1.3%
    2019
    +0.16
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1741
    +0.36
    0.03
    16
    +0.20
    0.13
    2019
    +0.16
    0.14
    Negative Logits
    <bos>
    -3.76
    ⓧ
    -0.75
    /***
    -0.74
    ///**
    -0.72
    PerformLayout
    -0.70
    expandindo
    -0.68
    writeFieldEnd
    -0.65
    devServer
    -0.64
     onCreateView
    -0.64
    ContentAsync
    -0.63
    POSITIVE LOGITS
     affor
    1.65
     accla
    1.57
     Juf
    1.56
     increa
    1.53
     volunte
    1.52
     Minang
    1.52
     inev
    1.46
     maneu
    1.46
     reluct
    1.45
     Keny
    1.45
    Activations Density 1.949%

    No Known Activations