© 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. 85
    Prev
    Next
    INDEX
    Explanations

    references to the European Handball Championship

    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
    1.2%
    1034
    +0.08
    0.3%
    1323
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    76
    +0.28
    0.00
    296
    +0.08
    0.00
    279
    +0.08
    0.00
    Negative Logits
    <bos>
    -2.22
    ⓧ
    -0.87
    
    -0.77
    <?
    -0.70
    <?
    -0.69
     rehabilitate
    -0.68
    /***
    -0.65
     PREVENT
    -0.62
     endow
    -0.62
     disarm
    -0.61
    POSITIVE LOGITS
     kafe
    1.10
     seksi
    1.09
     silikon
    0.99
     mikrofon
    0.95
     maksi
    0.95
     véhic
    0.94
     kosme
    0.92
     kaos
    0.91
     keramik
    0.88
     Karakter
    0.87
    Activations Density 0.000%

    No Known Activations