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

    Neuronpedia

    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. 275
    Prev
    Next
    INDEX
    Explanations

    instances of neglect or oversight in analysis or reporting

    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
    +0.24
    0.8%
    198
    +0.10
    0.3%
    1265
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1477
    +0.24
    0.05
    639
    +0.10
    0.04
    1372
    +0.07
    0.04
    Negative Logits
    <bos>
    -2.51
    
    -0.63
    <?
    -0.56
     finalize
    -0.55
    /*++
    -0.55
    numerusform
    -0.55
    /**
    -0.54
    //{
    -0.52
    💼
    -0.52
    ///**
    -0.52
    POSITIVE LOGITS
     Pourtant
    0.98
     Joaqu
    0.94
     churrasco
    0.94
     sappi
    0.89
     Juf
    0.89
     Khart
    0.88
     Karang
    0.87
    capulco
    0.87
     soggior
    0.87
     ados
    0.87
    Activations Density 0.467%

    No Known Activations