© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 3537
    Prev
    Next
    INDEX
    Explanations

    keywords related to healthcare access and quality

    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
    50
    +0.31
    1.2%
    1842
    +0.16
    0.6%
    1253
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1842
    +0.31
    0.04
    1385
    +0.16
    0.07
    908
    +0.09
    0.03
    Negative Logits
    <bos>
    -2.18
     intersper
    -1.11
     encomp
    -1.09
    
    -1.09
     quitted
    -0.99
    ⓧ
    -0.94
    /**
    -0.92
    <?
    -0.92
     Mlle
    -0.89
     reconno
    -0.86
    POSITIVE LOGITS
     teras
    0.88
     kafe
    0.74
     montagna
    0.72
     spiaggia
    0.67
     bandung
    0.67
     démoc
    0.66
     optik
    0.66
    capulco
    0.65
     bagay
    0.65
     silikon
    0.64
    Activations Density 0.669%

    No Known Activations