© 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. 0-RES-JB
    11. 831
    Prev
    Next
    INDEX
    Explanations

    phrases related to religious experiences and the relationship with God

    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.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1265
    +0.08
    0.3%
    1051
    +0.07
    0.2%
    687
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    753
    +0.08
    0.03
    1525
    +0.07
    0.03
    1637
    +0.06
    0.03
    Negative Logits
     also
    -0.89
     in
    -0.89
     си
    -0.87
    ‌
    -0.87
     now
    -0.86
     won
    -0.84
     really
    -0.84
     and
    -0.84
     once
    -0.84
     should
    -0.84
    POSITIVE LOGITS
     affor
    2.40
     scrat
    2.39
     stockholm
    2.35
     considér
    2.32
     impra
    2.30
     Chapitre
    2.28
     lidl
    2.27
     eiffel
    2.25
     unden
    2.24
     michelin
    2.22
    Activations Density 0.185%

    No Known Activations