© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 1516
    Prev
    Next
    INDEX
    Explanations

    temporal references and transitions in narratives

    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
    +0.21
    0.9%
    1438
    +0.12
    0.5%
    184
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1265
    +0.21
    0.05
    971
    +0.12
    0.05
    814
    +0.11
    0.05
    Negative Logits
    <bos>
    -2.84
    /***
    
    -0.89
    //----
    -0.78
    //---
    -0.76
     "..\..\..\
    -0.72
    ///**
    -0.70
    //--
    -0.68
    /*@
    -0.67
    beforeAll
    -0.67
    Enlaces
    -0.67
    POSITIVE LOGITS
     thuy
    1.52
     jaya
    1.44
     quoc
    1.40
     bandung
    1.33
     lele
    1.33
     nuoc
    1.29
     aen
    1.28
     Minang
    1.24
     kase
    1.21
     kasa
    1.20
    Activations Density 0.460%

    No Known Activations