© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 1660
    Prev
    Next
    INDEX
    Explanations

    repetitive patterns or occurrences in events or actions

    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
    +0.27
    0.9%
    297
    +0.07
    0.3%
    1173
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1473
    +0.27
    0.03
    1820
    +0.07
    0.03
    1167
    +0.07
    0.03
    Negative Logits
    <bos>
    -2.43
    /***
    
    -0.70
    ///**
    -0.70
    
    -0.67
     AssemblyCompany
    -0.61
    ⓧ
    -0.58
    
    
    -0.54
    XmlType
    -0.54
    sizeCache
    -0.53
    <?
    -0.52
    POSITIVE LOGITS
     Confu
    0.79
     philanth
    0.78
     bordeaux
    0.75
     Alcalde
    0.75
     nutella
    0.73
     starbucks
    0.72
     maroc
    0.72
     uefa
    0.71
     tupperware
    0.71
     Guel
    0.70
    Activations Density 0.115%

    No Known Activations