© 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. 4932
    Prev
    Next
    INDEX
    Explanations

    expressions of strong negative emotions or criticisms

    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
    +0.21
    0.8%
    1473
    +0.12
    0.4%
    382
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1473
    +0.21
    0.07
    1307
    +0.12
    0.06
    1577
    +0.10
    0.08
    Negative Logits
    <bos>
    -2.85
        
    -0.76
          
    -0.76
    CreateIndex
    -0.74
            
    -0.74
    glMatrixMode
    -0.74
    CreateMap
    -0.73
                      
    -0.73
                   
    -0.73
           
    -0.73
    POSITIVE LOGITS
     Juf
    1.86
     fta
    1.84
     maneu
    1.80
     mef
    1.79
     jaya
    1.79
     Minang
    1.77
     hcm
    1.77
     ftu
    1.77
     accla
    1.76
     Augu
    1.75
    Activations Density 0.739%

    No Known Activations