© 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. 4799
    Prev
    Next
    INDEX
    Explanations

    references to government officials and political roles

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    453
    +0.20
    0.8%
    50
    +0.17
    0.6%
    227
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.20
    0.09
    761
    +0.17
    0.07
    453
    +0.15
    0.07
    Negative Logits
    <bos>
    -2.84
     intersper
    -1.00
     encomp
    -0.79
     overcrow
    -0.79
    /***
    -0.73
     disambigu
    -0.73
     underval
    -0.67
     localize
    -0.65
     condense
    -0.64
     disbur
    -0.64
    POSITIVE LOGITS
     Spani
    0.81
     keramik
    0.77
     argint
    0.74
     mikrofon
    0.72
     silikon
    0.72
     hunde
    0.71
     kosme
    0.70
     Singapur
    0.69
     RSSSF
    0.68
     marea
    0.68
    Activations Density 0.388%

    No Known Activations