© 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. 5109
    Prev
    Next
    INDEX
    Explanations

    references to the word "Ba" in various contexts

    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
    1961
    +0.15
    0.9%
    50
    +0.15
    0.9%
    971
    +0.14
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1964
    +0.15
    0.02
    1622
    +0.15
    0.02
    971
    +0.14
    0.02
    Negative Logits
    <bos>
    -2.25
     int
    -0.58
     commission
    -0.55
    int
    -0.53
     Commission
    -0.53
    件事情
    -0.52
    Connell
    -0.52
     obj
    -0.52
    Посилання
    -0.52
    委员会
    -0.51
    POSITIVE LOGITS
     Ba
    1.43
     Baumann
    1.35
    Ba
    1.33
     maneu
    1.25
     Simult
    1.19
     baf
    1.18
     Baile
    1.17
     Bartholo
    1.16
     italia
    1.15
     napoli
    1.15
    Activations Density 0.076%

    No Known Activations