© 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. 1055
    Prev
    Next
    INDEX
    Explanations

    phrases related to Christianity and religious figures, specifically focusing on Jesus Christ

    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
    50
    +0.12
    1.1%
    1381
    +0.02
    0.2%
    1065
    +0.02
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1253
    +0.12
    0.06
    544
    +0.02
    0.07
    438
    +0.02
    0.07
    Negative Logits
    <bos>
    -2.21
    ⓧ
    -1.18
    
    -1.09
    /**
    -1.06
    <?
    -1.02
    /*
    -0.99
    <?
    -0.85
    public
    -0.84
     continue
    -0.83
    ,
    -0.82
    POSITIVE LOGITS
     stockholm
    2.08
     wien
    2.08
     affor
    1.97
     aen
    1.96
     Juf
    1.96
     mef
    1.93
     maneu
    1.92
     maroc
    1.91
     fta
    1.91
     increa
    1.91
    Activations Density 1.848%

    No Known Activations