© 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. 10-RES-JB
    11. 1310
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly commas

    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
    +0.34
    1.6%
    2019
    +0.16
    0.8%
    1265
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    814
    +0.34
    0.04
    1265
    +0.16
    0.04
    1568
    +0.09
    0.04
    Negative Logits
    <bos>
    -2.95
    ⓧ
    -1.12
     intersper
    -1.11
     encomp
    -1.02
    <?
    -1.00
    <?
    -0.96
    /***
    -0.96
    
    -0.95
     recipro
    -0.95
     pessi
    -0.94
    POSITIVE LOGITS
    pylab
    0.68
     “
    0.62
    cupertino
    0.59
    slidesPer
    0.58
    isnan
    0.57
    xlim
    0.55
     ‘
    0.54
    ModelMap
    0.54
     pylab
    0.54
    UITextField
    0.53
    Activations Density 0.141%

    No Known Activations