© 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. 5000
    Prev
    Next
    INDEX
    Explanations

    evaluative phrases regarding the quality or significance of written works

    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
    +0.30
    1.2%
    1150
    +0.13
    0.5%
    872
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    872
    +0.30
    0.09
    289
    +0.13
    0.06
    1380
    +0.11
    0.03
    Negative Logits
    <bos>
    -2.25
    ⓧ
    -1.01
    /**
    -0.82
    /***
    -0.79
    
    -0.71
     Chapitre
    -0.70
    /*
    -0.69
    <?
    -0.69
    Transkript
    -0.64
     /**
    -0.64
    POSITIVE LOGITS
     disad
    0.71
     disreg
    0.68
     Minangkabau
    0.66
     revan
    0.64
     thuy
    0.64
     maneu
    0.64
     calum
    0.62
     esser
    0.60
    jectures
    0.60
     belliger
    0.58
    Activations Density 1.106%

    No Known Activations