© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 2156
    Prev
    Next
    INDEX
    Explanations

    names of rugby players

    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
    1.6%
    1967
    +0.16
    1.0%
    1145
    +0.15
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.26
    0.14
    577
    +0.16
    0.09
    227
    +0.15
    0.13
    Negative Logits
    <bos>
    -2.73
    ⓧ
    -0.70
    ///**
    -0.67
     Мексичка
    -0.64
    /***
    -0.62
    avadoc
    -0.61
     become
    -0.61
     وعد
    -0.60
    /**
    -0.60
    ంట
    -0.59
    POSITIVE LOGITS
     Confu
    1.41
     paula
    1.35
     jorge
    1.34
     indestru
    1.31
     unlaw
    1.30
     impra
    1.29
     accla
    1.28
     ricardo
    1.28
     increa
    1.27
     sandra
    1.25
    Activations Density 1.597%

    No Known Activations