© 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. 246
    Prev
    Next
    INDEX
    Explanations

    references to the concept of existence or location, particularly through the use of the word "there."

    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
    +0.27
    1.3%
    814
    +0.11
    0.6%
    341
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    814
    +0.27
    0.04
    1491
    +0.11
    0.03
    341
    +0.11
    0.03
    Negative Logits
    <bos>
    -2.90
    //---
    -0.63
    /***
    -0.59
    #![
    -0.57
    /*++
    -0.55
    Более
    -0.54
    Тру
    -0.54
     seek
    -0.53
     rehabilitate
    -0.51
    ///**
    -0.51
    POSITIVE LOGITS
     maroc
    1.19
     seksi
    0.96
     ankara
    0.94
     bordeaux
    0.94
     signora
    0.93
     ecru
    0.93
     romero
    0.92
     bambina
    0.92
     cartier
    0.92
     paradiso
    0.91
    Activations Density 0.048%

    No Known Activations