© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES-JB
    11. 2346
    Prev
    Next
    INDEX
    Explanations

    references to the concept of 'sin' and related notions of moral judgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1328
    +0.19
    1.1%
    50
    +0.16
    0.9%
    971
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1328
    +0.19
    0.03
    442
    +0.16
    0.02
    1045
    +0.14
    0.02
    Negative Logits
    <bos>
    -2.51
    lateinit
    -0.81
    HomeAsUpEnabled
    -0.71
     const
    -0.67
    marshaller
    -0.67
    else
    -0.65
    const
    -0.65
    override
    -0.62
    ్రామ
    -0.61
    displayquote
    -0.61
    POSITIVE LOGITS
     unlaw
    1.49
     affor
    1.47
     fortn
    1.42
     Sinal
    1.42
     véhic
    1.42
     pymysql
    1.38
     Juf
    1.38
     reluct
    1.38
     soulign
    1.37
     impra
    1.37
    Activations Density 0.068%

    No Known Activations