© 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. 1478
    Prev
    Next
    INDEX
    Explanations

    technical jargon or variables related to programming and image processing

    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
    +0.16
    0.8%
    1343
    +0.16
    0.8%
    680
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.16
    0.09
    1978
    +0.16
    0.07
    506
    +0.12
    0.04
    Negative Logits
    <bos>
    -2.70
    ⓧ
    -1.14
    /**
    -1.12
    <?
    -1.08
    
    
    -0.98
    /*
    -0.86
    <?
    
    -0.77
     autorytatywna
    -0.70
     rehabilitate
    -0.61
    /***
    
    -0.61
    POSITIVE LOGITS
     karton
    1.14
     kafe
    1.09
     lele
    1.09
     keramik
    1.07
     seksi
    1.07
     silikon
    1.07
     alkoh
    0.99
     bunda
    0.99
     uhr
    0.98
     lemp
    0.97
    Activations Density 0.185%

    No Known Activations