© 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. 5119
    Prev
    Next
    INDEX
    Explanations

    mentions of legal or regulatory investigations and issues regarding accountability

    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
    1842
    +0.33
    1.6%
    1177
    +0.25
    1.2%
    394
    +0.19
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1842
    +0.33
    0.11
    1177
    +0.25
    0.02
    1499
    +0.19
    0.12
    Negative Logits
    <bos>
    -2.95
    ⓧ
    -0.93
    StoreMessageInfo
    -0.72
    
    -0.70
    <?
    -0.70
    //*/
    -0.65
    <>
    -0.65
     Normdatei
    -0.64
    USTAIN
    -0.63
    expandindo
    -0.62
    POSITIVE LOGITS
     Juf
    1.09
     saar
    1.02
     Khart
    0.93
     maksi
    0.93
     Strukt
    0.91
     Schrö
    0.90
     Breslau
    0.88
     kristal
    0.88
     optik
    0.88
     hina
    0.88
    Activations Density 2.667%

    No Known Activations