Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 938
    Prev
    Next
    INDEX
    Explanations

    sentences that end with a period

    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
    +0.19
    0.9%
    2034
    +0.16
    0.8%
    1323
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2034
    +0.19
    0.04
    382
    +0.16
    0.03
    1323
    +0.13
    0.03
    Negative Logits
    <bos>
    -2.28
    /**
    -1.31
    ⓧ
    -1.24
    <?
    -1.17
    
    
    -1.09
    /*
    -0.98
    <?
    
    -0.84
    /***
    
    -0.83
    ///**
    -0.72
    Może
    -0.70
    POSITIVE LOGITS
     lele
    0.96
    karet
    0.85
     thuy
    0.85
     Karakter
    0.84
     bandung
    0.82
     maroc
    0.82
     kram
    0.81
     antik
    0.80
     mû
    0.80
     ananas
    0.80
    Activations Density 0.057%

    No Known Activations