© 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. 4922
    Prev
    Next
    INDEX
    Explanations

    actions and behaviors related to creation and participation in various activities

    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
    +0.26
    1.0%
    1842
    +0.13
    0.5%
    1343
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1820
    +0.26
    0.05
    1148
    +0.13
    0.05
    1539
    +0.10
    0.03
    Negative Logits
    <bos>
    -2.38
    /***
    -0.82
    ValueGenerated
    -0.67
    ⓧ
    -0.61
     however
    -0.55
    Пол
    -0.54
    }{||
    -0.53
    
    -0.53
    <eos>
    -0.53
     but
    -0.52
    POSITIVE LOGITS
     saar
    1.34
     lele
    1.30
     aen
    1.29
     bloss
    1.26
     territo
    1.22
     wien
    1.22
     meis
    1.21
     franz
    1.19
     jaya
    1.18
     kasa
    1.18
    Activations Density 0.556%

    No Known Activations