© 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. 394
    Prev
    Next
    INDEX
    Explanations

    mentions of wrestling matches and related terms

    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
    +0.21
    0.8%
    1842
    +0.12
    0.5%
    304
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.21
    0.03
    121
    +0.12
    0.02
    823
    +0.10
    0.02
    Negative Logits
    <bos>
    -2.40
    ⓧ
    -0.76
     anhyd
    -0.70
     AssemblyProduct
    -0.69
    GEBURTSDATUM
    -0.69
    InjectAttribute
    -0.69
    
    
    -0.68
    /*
    -0.68
    /***
    
    -0.67
     EconPapers
    -0.63
    POSITIVE LOGITS
     Yugos
    0.93
     accla
    0.81
     McLaugh
    0.80
     Czechos
    0.79
     Heere
    0.78
     philanth
    0.78
     McInt
    0.77
     Sted
    0.76
     unspeak
    0.75
     maneu
    0.72
    Activations Density 0.180%

    No Known Activations