© 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. 3264
    Prev
    Next
    INDEX
    Explanations

    instances of the word "strategy."

    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
    +0.26
    1.6%
    1870
    +0.14
    0.8%
    555
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    251
    +0.26
    0.03
    555
    +0.14
    0.03
    1806
    +0.14
    0.03
    Negative Logits
    <bos>
    -2.72
    /***
    -0.85
    
    -0.71
    ⓧ
    -0.67
    //---
    -0.66
    <?
    -0.66
    ///**
    -0.65
    /*!
    -0.58
     /**
    -0.58
    //*/
    -0.57
    POSITIVE LOGITS
     strategia
    1.32
     strategy
    1.26
     Strategy
    1.15
    strategy
    1.13
     STRATEGY
    1.09
    Strategy
    1.06
     thuy
    1.05
     strategies
    1.05
     strategie
    0.99
    strategia
    0.99
    Activations Density 0.033%

    No Known Activations