© 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. 5130
    Prev
    Next
    INDEX
    Explanations

    references to biblical figures and stories

    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
    +0.19
    0.7%
    1842
    +0.16
    0.6%
    394
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1307
    +0.19
    0.05
    227
    +0.16
    0.06
    1741
    +0.13
    0.01
    Negative Logits
    <bos>
    -2.39
     autorytatywna
    -1.09
    Autoritní
    -1.07
     initComponents
    -0.96
     Paglinawan
    -0.89
     PeEnEo
    -0.88
    SequentialGroup
    -0.84
    IonicModule
    -0.84
     وتسجيلات
    -0.83
    @[+][
    -0.82
    POSITIVE LOGITS
     impra
    1.92
     maneu
    1.88
     increa
    1.87
     disagre
    1.78
     reluct
    1.78
     affor
    1.73
     indestru
    1.73
     horrend
    1.72
     shenan
    1.71
     disreg
    1.70
    Activations Density 0.331%

    No Known Activations