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. 6-RES-JB
    6. 9000
    Prev
    Next
    INDEX
    Explanations

    phrases relating to personal, familial, or community experiences

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.30
    1.6%
    1984
    +0.10
    0.5%
    1967
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1984
    +0.30
    0.07
    1937
    +0.10
    0.06
    144
    +0.09
    0.06
    Negative Logits
    <bos>
    -3.14
    /***
    
    -0.92
    
    
    -0.83
    /**
    -0.78
    <?
    -0.77
    <?
    
    -0.73
    /*
    -0.67
    ///**
    -0.64
    ⓧ
    -0.63
    },{
    
    -0.61
    POSITIVE LOGITS
     Muhamma
    0.90
     Jambi
    0.87
     teneb
    0.86
     valencia
    0.85
     albic
    0.82
     Minang
    0.82
     Pekan
    0.81
     azule
    0.81
     seksi
    0.80
     Palembang
    0.78
    Activations Density 0.321%

    No Known Activations