© 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. 5108
    Prev
    Next
    INDEX
    Explanations

    references to legislative actions and statements from political figures

    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
    +0.33
    1.3%
    604
    +0.13
    0.5%
    1499
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1048
    +0.33
    0.06
    1499
    +0.13
    0.07
    453
    +0.12
    0.07
    Negative Logits
    <bos>
    -3.04
     intersper
    -0.95
     nutella
    -0.88
    /***
    -0.87
    ⓧ
    -0.86
     endow
    -0.85
     overcrow
    -0.76
     /**
    -0.74
     frites
    -0.73
     gratify
    -0.72
    POSITIVE LOGITS
     Minang
    0.88
     Muhamma
    0.84
     Pekan
    0.76
    Atsauces
    0.75
     nikah
    0.73
    :"-
    0.72
     Jambi
    0.72
     Palembang
    0.72
     jati
    0.69
     KPK
    0.68
    Activations Density 0.738%

    No Known Activations