© 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. 307
    Prev
    Next
    INDEX
    Explanations

    references to Lebanon and its political context

    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
    1137
    +0.14
    0.7%
    517
    +0.13
    0.7%
    50
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.14
    0.03
    517
    +0.13
    0.02
    62
    +0.12
    0.02
    Negative Logits
    <bos>
    -2.15
    +#+#
    -0.65
    எ
    -0.61
    //{
    
    -0.59
    //}
    
    -0.59
    /***
    
    -0.58
    Ян
    -0.57
    /**
    -0.56
    //};
    -0.56
    ngOn
    -0.56
    POSITIVE LOGITS
     🤣🤣
    1.27
     unspeak
    1.25
     unwarran
    1.21
     😍😍
    1.17
     indescri
    1.17
     fta
    1.15
     thut
    1.15
     ❤️❤️
    1.13
     Lebanon
    1.11
    Lebanon
    1.07
    Activations Density 0.101%

    No Known Activations