© 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. 10-RES-JB
    11. 3420
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and references in written content

    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
    +0.30
    1.1%
    1842
    +0.07
    0.3%
    1372
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1674
    +0.30
    0.05
    973
    +0.07
    0.05
    1642
    +0.07
    0.05
    Negative Logits
    <bos>
    -1.83
    ⓧ
    -0.98
    
    -0.71
    <?
    -0.68
     springfox
    -0.68
    /**
    -0.66
    /*
    -0.62
    InjectAttribute
    -0.61
    ByVersion
    -0.61
    /***
    -0.58
    POSITIVE LOGITS
     seksi
    0.87
     ados
    0.80
     jajaja
    0.77
     accla
    0.75
     bandung
    0.74
     Putih
    0.71
     lancia
    0.70
     istan
    0.69
     ducato
    0.69
     maneu
    0.69
    Activations Density 0.092%

    No Known Activations