© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10-RES-JB
    11. 1272
    Prev
    Next
    INDEX
    Explanations

    phrases related to communication and inquiries

    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
    +0.29
    1.1%
    453
    +0.17
    0.6%
    1150
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    747
    +0.29
    0.04
    1992
    +0.17
    0.04
    453
    +0.13
    0.04
    Negative Logits
    <bos>
    -2.48
    {?>
    -0.62
    uxxxx
    -0.61
    ⓧ
    -0.57
    FunctionFlags
    -0.56
    AsUp
    -0.55
    richTextPanel
    -0.55
    Panamoan
    -0.54
     ModelRenderer
    -0.53
     habet
    -0.52
    POSITIVE LOGITS
     maneu
    1.03
     accla
    0.93
     Karang
    0.91
     unspeak
    0.91
     Khart
    0.90
     soulign
    0.90
     pymysql
    0.88
     Jambi
    0.88
     smtplib
    0.86
     viciss
    0.86
    Activations Density 0.114%

    No Known Activations