© 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. 10-RES-JB
    11. 4845
    Prev
    Next
    INDEX
    Explanations

    phrases related to moral responsibility and accountability in discussions

    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
    1343
    +0.21
    1.0%
    50
    +0.20
    0.9%
    599
    +0.16
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    599
    +0.21
    0.14
    1129
    +0.20
    0.09
    184
    +0.16
    0.01
    Negative Logits
    <bos>
    -3.21
    ⓧ
    -1.07
    /***
    -0.94
    <?
    -0.84
    
    -0.80
    /*!
    -0.78
    <?
    -0.73
     inaugurate
    -0.70
    /**
    -0.67
    Dzięki
    -0.66
    POSITIVE LOGITS
     sement
    1.23
     loto
    1.20
     hunde
    1.19
     thuy
    1.19
     utop
    1.18
     tyn
    1.18
     torba
    1.17
     silikon
    1.16
     indeb
    1.15
     kaos
    1.14
    Activations Density 1.284%

    No Known Activations