© 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. 1295
    Prev
    Next
    INDEX
    Explanations

    prepositions indicating various contexts or relationships

    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
    +0.24
    1.0%
    405
    +0.12
    0.5%
    1562
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1416
    +0.24
    0.02
    101
    +0.12
    0.03
    1581
    +0.12
    0.02
    Negative Logits
    <bos>
    -2.12
    ⓧ
    -0.89
    <?
    -0.67
    /**
    -0.63
    /*
    -0.63
    Tikang
    -0.63
    RTEX
    -0.58
    //
    -0.56
    
    -0.55
     /**
    -0.54
    POSITIVE LOGITS
     maneu
    0.86
     tupperware
    0.85
     ecru
    0.80
     papilla
    0.79
     wattpad
    0.79
     jaya
    0.78
     venant
    0.78
     accla
    0.78
     ankara
    0.78
     récomp
    0.78
    Activations Density 0.158%

    No Known Activations