© 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. 4938
    Prev
    Next
    INDEX
    Explanations

    references to measurements or numerical data in a structured format

    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
    1967
    +0.24
    0.8%
    1699
    +0.13
    0.5%
    478
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1967
    +0.24
    0.00
    495
    +0.13
    0.00
    478
    +0.12
    0.00
    Negative Logits
    <bos>
    -2.50
     intersper
    -1.90
     hentai
    -1.72
     disagre
    -1.68
     milf
    -1.67
     snoopy
    -1.67
     hairc
    -1.62
     pamph
    -1.62
     superintend
    -1.61
     swarovski
    -1.60
    POSITIVE LOGITS
    2
    0.72
    mathrm
    0.70
    0
    0.67
    1
    0.67
    󠁢
    0.66
    3
    0.63
    end
    0.61
    H
    0.61
    4
    0.61
    5
    0.60
    Activations Density 0.002%

    No Known Activations