© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 3016
    Prev
    Next
    INDEX
    Explanations

    intensifiers and extreme descriptors, particularly those related to the word "incredible."

    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
    478
    +0.22
    1.2%
    1806
    +0.16
    0.9%
    172
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    478
    +0.22
    0.03
    1056
    +0.16
    0.02
    1776
    +0.14
    0.02
    Negative Logits
    <bos>
    -1.61
    /***
    -0.58
    ///**
    -0.58
    washingtonpost
    -0.58
    dat
    -0.54
    #![
    -0.53
     Marcia
    -0.51
     Lydia
    -0.51
    nosotros
    -0.50
    /*!
    -0.50
    POSITIVE LOGITS
     lele
    1.21
     jaya
    1.20
     seksi
    1.20
     saar
    1.18
     saha
    1.14
     kasa
    1.14
     hina
    1.12
     kark
    1.09
     kado
    1.04
     Minang
    1.03
    Activations Density 0.109%

    No Known Activations