© 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. 5018
    Prev
    Next
    INDEX
    Explanations

    structured data or code snippets related to objects and elements

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    856
    +0.23
    1.1%
    394
    +0.13
    0.6%
    845
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1445
    +0.23
    0.06
    1699
    +0.13
    0.06
    924
    +0.13
    0.04
    Negative Logits
    <bos>
    -2.90
    
    -1.33
    ⓧ
    -1.31
    <?
    -1.22
    /**
    -1.22
    /*
    -0.98
    #![
    -0.84
    <?
    -0.83
    /*!
    -0.80
     springfox
    -0.80
    POSITIVE LOGITS
     lele
    1.05
     bandung
    0.98
     jaya
    0.96
     jawa
    0.94
     gila
    0.94
     maroc
    0.93
     unlaw
    0.90
     Cik
    0.88
     tramont
    0.87
     disreg
    0.86
    Activations Density 0.578%

    No Known Activations