© 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. 0-RES-JB
    11. 2805
    Prev
    Next
    INDEX
    Explanations

    information about individuals including their personal details, education background, and employment history

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    752
    +0.08
    0.3%
    50
    +0.07
    0.3%
    1661
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    530
    +0.08
    0.04
    747
    +0.07
    0.04
    1845
    +0.06
    0.04
    Negative Logits
    <bos>
    -1.32
     continue
    -0.98
    ,
    -0.95
     be
    -0.95
     in
    -0.93
    .
    -0.93
     do
    -0.93
     on
    -0.91
     for
    -0.90
     at
    -0.90
    POSITIVE LOGITS
     maneu
    2.66
     affor
    2.64
     strick
    2.55
     fta
    2.49
     ftu
    2.48
     increa
    2.48
     accla
    2.47
     véhic
    2.46
     scrat
    2.44
     guarante
    2.44
    Activations Density 0.081%

    No Known Activations