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. 1059
    Prev
    Next
    INDEX
    Explanations

    references to influential books and public reactions to them

    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
    +0.29
    1.2%
    184
    +0.23
    1.0%
    604
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.29
    0.02
    1531
    +0.23
    0.05
    344
    +0.15
    0.05
    Negative Logits
    <bos>
    -3.19
     /**
    
    -0.85
    ///**
    -0.84
    /***
    
    -0.80
    //*/
    -0.73
    /*!
    
    -0.69
    /**
    
    
    -0.67
    <>
    
    -0.65
    //<
    -0.60
    //--
    -0.59
    POSITIVE LOGITS
     Khart
    1.08
     Minang
    1.07
     Juf
    1.01
     fortn
    0.97
     maneu
    0.97
     Palembang
    0.94
     Jambi
    0.94
     quoique
    0.92
     Keny
    0.92
     Karang
    0.91
    Activations Density 0.884%

    No Known Activations