© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 3476
    Prev
    Next
    INDEX
    Explanations

    phrases related to educational institutions and procedures, specifically around student services and administrative guidelines

    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
    +0.23
    1.5%
    544
    +0.08
    0.5%
    1527
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1691
    +0.23
    0.05
    1527
    +0.08
    0.04
    1406
    +0.08
    0.04
    Negative Logits
    <bos>
    -3.26
    ⓧ
    -1.05
    <?
    -0.86
    /**
    -0.82
    
    -0.73
    /*
    -0.68
    /*++
    -0.66
     AssemblyCompany
    -0.64
    <?
    -0.63
    /***
    -0.62
    POSITIVE LOGITS
     véhic
    1.22
     maksi
    1.11
     seksi
    1.08
     Khart
    1.04
     silikon
    1.03
     keramik
    1.03
     Meksi
    1.01
     lele
    0.99
     soulign
    0.99
     Students
    0.99
    Activations Density 0.083%

    No Known Activations