© 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. 5051
    Prev
    Next
    INDEX
    Explanations

    instances of the word "dangerous" and its variations

    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
    +0.26
    1.4%
    468
    +0.10
    0.6%
    341
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    468
    +0.26
    0.03
    869
    +0.10
    0.03
    765
    +0.10
    0.03
    Negative Logits
    <bos>
    -3.38
    append
    -0.73
    fileprivate
    -0.71
    AllowUser
    -0.70
    })();
    -0.70
    IEnumerator
    -0.70
    struct
    -0.69
    glBindBuffer
    -0.69
    AddColumn
    -0.69
    printf
    -0.69
    POSITIVE LOGITS
     riviera
    1.91
     casio
    1.89
     milano
    1.88
     swarovski
    1.87
     ibiza
    1.87
     bordeaux
    1.86
     napoli
    1.85
     dises
    1.84
     eiffel
    1.84
     lamborghini
    1.82
    Activations Density 0.055%

    No Known Activations