© 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. 5008
    Prev
    Next
    INDEX
    Explanations

    references to location and context-setting details

    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
    +0.31
    1.4%
    394
    +0.30
    1.4%
    964
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    394
    +0.31
    0.19
    766
    +0.30
    0.10
    964
    +0.10
    0.09
    Negative Logits
    <bos>
    -2.69
    .
    -0.69
    PerformLayout
    -0.67
    XmlAccessType
    -0.63
    Anhalt
    -0.63
    
    -0.62
    GraphicsUnit
    -0.62
     mxArray
    -0.61
    /*
    -0.61
    。
    -0.61
    POSITIVE LOGITS
     maneu
    1.83
     increa
    1.74
     affor
    1.71
     inev
    1.65
     unwarran
    1.61
     impra
    1.60
     disagre
    1.60
     reluct
    1.58
     accla
    1.57
     uninten
    1.57
    Activations Density 3.198%

    No Known Activations