© 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. 2446
    Prev
    Next
    INDEX
    Explanations

    terms related to memorials and significant historical references

    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
    +0.25
    0.9%
    845
    +0.11
    0.4%
    1150
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1870
    +0.25
    0.07
    845
    +0.11
    0.08
    2032
    +0.10
    0.08
    Negative Logits
    <bos>
    -2.47
    <?
    -0.92
    #![
    -0.86
    /*
    -0.85
    ⓧ
    -0.79
    /**
    -0.77
    /*++
    -0.71
     שוליים
    -0.71
    
    -0.70
     Bourgoin
    -0.65
    POSITIVE LOGITS
     disagre
    2.13
     affor
    2.04
     reluct
    1.97
     impra
    1.96
     increa
    1.95
     maneu
    1.94
     accla
    1.94
     inev
    1.93
     shenan
    1.92
     unwarran
    1.87
    Activations Density 1.108%

    No Known Activations