© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 4847
    Prev
    Next
    INDEX
    Explanations

    words related to references or identifiers in a legal or formal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.25
    0.9%
    298
    +0.09
    0.3%
    1101
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    62
    +0.25
    0.03
    2
    +0.09
    0.03
    143
    +0.08
    0.02
    Negative Logits
    <bos>
    -2.63
    ⓧ
    -1.06
    <?
    -0.88
    
    -0.86
    /**
    -0.76
    /*++
    -0.74
     springfox
    -0.74
    /*
    -0.69
    +:+
    -0.67
    contentLoaded
    -0.61
    POSITIVE LOGITS
     🤣🤣
    0.94
     affor
    0.87
     😍😍
    0.82
     🥲
    0.81
     😭😭
    0.81
     ❤️❤️
    0.80
     lmfao
    0.79
     🙃
    0.78
     maneu
    0.77
     disgra
    0.76
    Activations Density 0.117%

    No Known Activations