© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 2445
    Prev
    Next
    INDEX
    Explanations

    references to lung cancer and related medical conditions

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1350
    +0.20
    1.1%
    303
    +0.15
    0.8%
    442
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1350
    +0.20
    0.02
    1741
    +0.15
    0.00
    1328
    +0.13
    0.02
    Negative Logits
    <bos>
    -1.16
    guang
    -0.59
    Allora
    -0.57
    <b>
    -0.53
     rheumatic
    -0.53
    liang
    -0.52
     relive
    -0.52
     Giuliano
    -0.50
     Liang
    -0.49
     shake
    -0.49
    POSITIVE LOGITS
     Lung
    1.12
    Lung
    1.05
     quæ
    1.04
     ejus
    1.00
     lung
    0.99
     eorum
    0.97
     cæ
    0.94
    lung
    0.88
     habet
    0.87
     lungs
    0.84
    Activations Density 0.139%

    No Known Activations