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. 6252
    Prev
    Next
    INDEX
    Explanations

    instances of numbers followed by a measurement unit, such as "25K" or "1M"

    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
    +0.34
    2.1%
    2019
    +0.22
    1.3%
    1967
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2019
    +0.34
    0.09
    1265
    +0.22
    0.08
    382
    +0.12
    0.09
    Negative Logits
    <bos>
    -3.81
    /***
    
    -0.99
    ⓧ
    -0.93
    <?
    -0.84
    ///**
    -0.77
    
    
    -0.71
    //*/
    -0.71
    Jeografia
    -0.69
    /**
    -0.69
    //---
    -0.67
    POSITIVE LOGITS
     Minang
    0.75
     marea
    0.71
     Tanjung
    0.68
     jawa
    0.68
     Palembang
    0.67
     uhr
    0.66
     saar
    0.66
     sappi
    0.65
     Banjar
    0.64
     bandung
    0.63
    Activations Density 0.769%

    No Known Activations