© 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. 4954
    Prev
    Next
    INDEX
    Explanations

    references to time and occurrences

    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
    +0.23
    0.9%
    1705
    +0.14
    0.6%
    1103
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1705
    +0.23
    0.04
    1265
    +0.14
    0.04
    683
    +0.10
    0.04
    Negative Logits
    <bos>
    -1.88
     дописавши
    -0.59
    ⓧ
    -0.57
    EndGlobalSection
    -0.57
    /***
    -0.56
    diff
    -0.51
    #![
    -0.50
     intersper
    -0.50
     disbur
    -0.49
    endwhile
    -0.49
    POSITIVE LOGITS
     asado
    0.98
    Somewhere
    0.91
     sement
    0.89
     Almería
    0.89
     Somewhere
    0.88
     mezza
    0.88
     churrasco
    0.87
     somewhere
    0.84
     cioc
    0.83
     palab
    0.81
    Activations Density 0.183%

    No Known Activations