© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 7111
    Prev
    Next
    INDEX
    Explanations

    text related to correspondence, letters, and messages in various contexts

    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
    +0.21
    0.8%
    1150
    +0.14
    0.6%
    946
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    946
    +0.21
    0.09
    1150
    +0.14
    0.05
    961
    +0.11
    0.08
    Negative Logits
    <bos>
    -2.66
    ⓧ
    -0.97
    /**
    -0.94
    <?
    -0.85
    /*
    -0.76
    
    -0.71
    /***
    -0.68
    equila
    -0.67
    /*++
    -0.63
    //}
    -0.62
    POSITIVE LOGITS
     maneu
    1.09
     philanth
    1.08
     unspeak
    1.01
     Minang
    0.98
     impra
    0.98
     practition
    0.98
     disagre
    0.95
     jawa
    0.94
     accla
    0.93
     exorbit
    0.93
    Activations Density 1.107%

    No Known Activations