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. 675
    Prev
    Next
    INDEX
    Explanations

    issues related to consumer products and their associated problems

    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
    +0.31
    1.6%
    2019
    +0.25
    1.3%
    1535
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2019
    +0.31
    0.07
    304
    +0.25
    0.01
    752
    +0.13
    0.04
    Negative Logits
    <bos>
    -3.35
    ⓧ
    -1.02
    /**
    -0.91
    
    
    -0.90
    /***
    
    -0.87
    <?
    -0.85
     disbur
    -0.77
    /*
    -0.76
    ///**
    -0.75
     springfox
    -0.74
    POSITIVE LOGITS
     maroc
    0.88
     marea
    0.86
     véhic
    0.80
     cartier
    0.79
     seksi
    0.79
     ados
    0.77
     mikrofon
    0.77
     kafe
    0.75
     karton
    0.73
     marte
    0.71
    Activations Density 0.166%

    No Known Activations