Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 1777
    Prev
    Next
    INDEX
    Explanations

    financial and resource-related terms, particularly in the context of international negotiations and agreements

    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
    1842
    +0.17
    0.6%
    50
    +0.12
    0.4%
    468
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1842
    +0.17
    0.06
    1385
    +0.12
    0.10
    1870
    +0.08
    0.05
    Negative Logits
    tagHelperRunner
    -0.85
     Leurs
    -0.73
     volon
    -0.73
    /***
    
    -0.71
     /**
    
    -0.68
    <bos>
    -0.68
     initComponents
    -0.67
    <?
    
    -0.66
     inserir
    -0.65
    &
    
    -0.65
    POSITIVE LOGITS
     autunno
    0.86
     spiaggia
    0.80
     carrefour
    0.80
     attesa
    0.80
     fabbrica
    0.78
     caccia
    0.78
     vacanza
    0.77
     paradiso
    0.76
     pavillon
    0.75
     cimetière
    0.74
    Activations Density 1.203%

    No Known Activations