© 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. 4990
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "better" in various forms

    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
    +0.24
    1.4%
    874
    +0.12
    0.7%
    1839
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1507
    +0.24
    0.04
    1127
    +0.12
    0.04
    75
    +0.11
    0.04
    Negative Logits
    <bos>
    -2.34
     rehabilitate
    -0.73
     expel
    -0.61
    <tfoot>
    -0.60
     condense
    -0.59
    //---
    -0.57
     reclaim
    -0.56
    glPushMatrix
    -0.56
     mobilize
    -0.55
     amass
    -0.55
    POSITIVE LOGITS
     ecru
    1.08
     hilux
    1.07
     chrysler
    1.06
     maroc
    1.06
     swarovski
    1.04
     isuzu
    1.02
     territo
    1.02
     shopee
    1.01
    better
    1.00
     maksi
    1.00
    Activations Density 0.072%

    No Known Activations