© 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. 4882
    Prev
    Next
    INDEX
    Explanations

    keywords related to digital currency and its ecosystem

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.28
    1.2%
    1870
    +0.17
    0.7%
    678
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1870
    +0.28
    0.09
    1013
    +0.17
    0.11
    1745
    +0.13
    0.08
    Negative Logits
    <bos>
    -2.27
    ുറ
    -0.70
    //---
    -0.67
    TargetException
    -0.66
     noten
    -0.66
    Demografía
    -0.64
     AssemblyCompany
    -0.64
    displayquote
    -0.63
     تضيفلها
    -0.62
     оригіналу
    -0.62
    POSITIVE LOGITS
     unlaw
    1.66
     impra
    1.57
     unwarran
    1.55
     embodi
    1.54
     churrasco
    1.52
     impractica
    1.51
     swarovski
    1.49
     ecru
    1.42
     Shakspeare
    1.41
     affor
    1.41
    Activations Density 1.203%

    No Known Activations