© 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. 8832
    Prev
    Next
    INDEX
    Explanations

    references to religious concepts and locations, particularly related to Christian beliefs and the afterlife such as heaven, hell, purgatory, and divine figures like Virgil

    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
    +0.20
    0.7%
    1842
    +0.08
    0.3%
    1356
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    509
    +0.20
    0.04
    2037
    +0.08
    0.05
    2015
    +0.07
    0.01
    Negative Logits
    <bos>
    -2.66
     AssemblyCompany
    -0.81
    public
    -0.76
    AccessorTable
    -0.73
    ByVersion
    -0.72
    mergeFrom
    -0.72
     esternos
    -0.70
     gynnwys
    -0.69
    MessageTagHelper
    -0.67
     initComponents
    -0.65
    POSITIVE LOGITS
     maneu
    1.53
     toledo
    1.47
     affor
    1.45
     Juf
    1.45
     🤣🤣
    1.41
     lidl
    1.41
     unlaw
    1.38
     véhic
    1.36
     Augu
    1.35
     philanth
    1.34
    Activations Density 0.343%

    No Known Activations