© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 3754
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics related to rankings and assessments

    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%
    856
    +0.12
    0.4%
    2034
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1081
    +0.19
    0.05
    856
    +0.12
    0.04
    500
    +0.10
    0.05
    Negative Logits
    <bos>
    -2.86
    ⓧ
    -0.87
    /**
    -0.85
    <?
    -0.84
    ///**
    -0.83
     kaynağından
    -0.77
    
    -0.68
    <?
    -0.67
    /*
    -0.67
     ProtoMessage
    -0.62
    POSITIVE LOGITS
     maneu
    1.07
     lele
    0.99
     Confu
    0.99
     shenan
    0.98
     disagre
    0.97
     kaos
    0.95
     reluct
    0.94
     excru
    0.94
     accla
    0.94
     impra
    0.91
    Activations Density 0.204%

    No Known Activations