© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 3166
    Prev
    Next
    INDEX
    Explanations

    references to various sectors and industries

    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
    +0.25
    1.5%
    1870
    +0.15
    0.9%
    1777
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1777
    +0.25
    0.02
    421
    +0.15
    0.01
    1491
    +0.11
    0.01
    Negative Logits
    <bos>
    -2.64
    <?
    -0.75
    ⓧ
    -0.74
    /**
    -0.72
    /*
    -0.71
    <?
    -0.70
     unify
    -0.70
    /***
    -0.66
     inaugurate
    -0.64
    //---
    -0.62
    POSITIVE LOGITS
     seksi
    1.37
     maksi
    1.36
     sektor
    1.34
     saad
    1.28
     saar
    1.26
     sector
    1.21
     naer
    1.19
     osal
    1.16
     Sector
    1.15
     keramik
    1.14
    Activations Density 0.021%

    No Known Activations