© 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. 1934
    Prev
    Next
    INDEX
    Explanations

    instances of the word "because" in various forms

    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
    +0.31
    1.7%
    1068
    +0.10
    0.6%
    1839
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1691
    +0.31
    0.05
    1068
    +0.10
    0.05
    920
    +0.10
    0.05
    Negative Logits
    <bos>
    -2.84
    /***
    -0.79
    ///**
    -0.62
    enter
    -0.56
     re
    -0.55
    ValueGenerated
    -0.55
     rein
    -0.54
     enter
    -0.54
    declare
    -0.53
    /*!
    -0.52
    POSITIVE LOGITS
     bandung
    1.48
     lele
    1.45
     kasa
    1.37
     Minang
    1.35
     kase
    1.30
     Muhamma
    1.28
     maksi
    1.27
     silikon
    1.26
     Karang
    1.24
     saar
    1.24
    Activations Density 0.101%

    No Known Activations