© 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. 4772
    Prev
    Next
    INDEX
    Explanations

    instances of the word “the” and related formatting variations

    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
    50
    +0.19
    0.7%
    2019
    +0.13
    0.5%
    1343
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1324
    +0.19
    0.04
    332
    +0.13
    0.04
    1267
    +0.13
    0.04
    Negative Logits
    <bos>
    -1.81
    /**
    -1.11
    ⓧ
    -1.03
    <?
    -0.96
    
    -0.95
     gratify
    -0.90
    /*
    -0.86
     nadzieję
    -0.82
     człowie
    -0.81
     nadzie
    -0.81
    POSITIVE LOGITS
     mikrofon
    0.95
     keramik
    0.94
     alkoh
    0.91
     monaster
    0.90
     silikon
    0.89
     karton
    0.85
     manuten
    0.84
     Veter
    0.82
     kosme
    0.81
     Departement
    0.81
    Activations Density 0.054%

    No Known Activations