© 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. 4758
    Prev
    Next
    INDEX
    Explanations

    notable events or changes in specific locations or situations

    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
    2019
    +0.24
    1.0%
    50
    +0.21
    0.9%
    1535
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2019
    +0.24
    0.05
    304
    +0.21
    0.01
    1445
    +0.12
    0.04
    Negative Logits
    <bos>
    -2.31
    ⓧ
    -1.30
    
    -1.08
    /***
    -1.08
    /**
    -1.07
    <?
    -1.02
    /*
    -0.80
    ///**
    -0.80
     springfox
    -0.77
    <?
    -0.77
    POSITIVE LOGITS
     soulign
    0.61
     épu
    0.61
     véhic
    0.59
     udang
    0.56
     résult
    0.56
    ffie
    0.56
     affich
    0.55
    efes
    0.54
     échou
    0.54
     nécess
    0.54
    Activations Density 0.096%

    No Known Activations