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. 827
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "America."

    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
    +0.26
    1.5%
    1296
    +0.17
    1.0%
    1565
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1296
    +0.26
    0.05
    1565
    +0.17
    0.03
    78
    +0.10
    0.03
    Negative Logits
    <bos>
    -3.15
    ⓧ
    -0.80
    /***
    
    -0.70
    
    
    -0.70
    /**
    -0.69
     defray
    -0.65
     endow
    -0.65
     mobilize
    -0.64
     waive
    -0.63
     disbur
    -0.63
    POSITIVE LOGITS
     Châ
    1.10
     Juf
    1.01
     Traité
    0.99
     Schrö
    0.98
     Kün
    0.95
     America
    0.95
     bourg
    0.93
     Amé
    0.92
     Heere
    0.91
     Aner
    0.91
    Activations Density 0.038%

    No Known Activations