© 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. 5132
    Prev
    Next
    INDEX
    Explanations

    tokens related to specific names, brands, or organizations

    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
    381
    +0.22
    0.9%
    1177
    +0.22
    0.8%
    678
    +0.19
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.22
    0.11
    981
    +0.22
    0.12
    1056
    +0.19
    0.10
    Negative Logits
    <bos>
    -1.22
    .
    -0.80
     erős
    -0.79
     sprawy
    -0.74
     næste
    -0.74
      
    -0.73
     자신의
    -0.73
     is
    -0.72
     (
    -0.72
     tæt
    -0.71
    POSITIVE LOGITS
     alkoh
    1.88
     silikon
    1.84
     kosme
    1.84
     mikrofon
    1.83
     antik
    1.78
     keramik
    1.75
     Strukt
    1.74
     Kategor
    1.70
     Pièces
    1.65
     Konkur
    1.65
    Activations Density 0.625%

    No Known Activations