© 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. 5064
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly quotation marks

    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
    +0.29
    1.4%
    2019
    +0.14
    0.7%
    1042
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1243
    +0.29
    0.08
    1042
    +0.14
    0.06
    527
    +0.10
    0.06
    Negative Logits
    <bos>
    -1.81
     intersper
    -1.09
     !...
    -0.96
     hentai
    -0.90
     bourgeo
    -0.89
     disambigu
    -0.87
    ///**
    -0.86
     vhs
    -0.84
    /***
    -0.83
     /**
    -0.81
    POSITIVE LOGITS
     récomp
    0.65
     spécialement
    0.65
     véhic
    0.65
     soulign
    0.64
     habituellement
    0.64
     coû
    0.60
     catég
    0.59
     énon
    0.59
     soigneusement
    0.59
     néanmoins
    0.57
    Activations Density 0.102%

    No Known Activations