© 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. 186
    Prev
    Next
    INDEX
    Explanations

    references to the national anthem

    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
    +0.28
    1.1%
    1150
    +0.12
    0.4%
    906
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1150
    +0.28
    0.02
    946
    +0.12
    0.04
    166
    +0.10
    0.04
    Negative Logits
    <bos>
    -2.18
    ⓧ
    -0.90
    /**
    -0.90
    /*
    -0.87
    <?
    -0.85
    
    -0.81
    JAKARTA
    -0.76
    Vegeu
    -0.74
    /***
    -0.72
    <?
    -0.64
    POSITIVE LOGITS
     maneu
    1.72
     disreg
    1.64
     shenan
    1.61
     emphat
    1.59
     practition
    1.55
     resear
    1.53
     Keny
    1.51
     accla
    1.51
     inev
    1.51
     reluct
    1.50
    Activations Density 0.743%

    No Known Activations