© 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. 171
    Prev
    Next
    INDEX
    Explanations

    dates and their occurrences in the document

    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
    +0.20
    1.1%
    1065
    +0.12
    0.6%
    1034
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    332
    +0.20
    0.03
    776
    +0.12
    0.04
    1267
    +0.11
    0.03
    Negative Logits
    <bos>
    -2.95
    ⓧ
    -1.09
    /**
    -0.92
    
    -0.80
    <?
    -0.77
    glPushMatrix
    -0.76
    וויק
    -0.73
    /*++
    -0.71
    /*
    -0.71
     "..\..\..\
    -0.71
    POSITIVE LOGITS
     maneu
    1.80
     increa
    1.72
     Juf
    1.68
     impra
    1.66
     affor
    1.64
     intermitt
    1.61
     wien
    1.59
     accla
    1.57
     compen
    1.57
     suscep
    1.56
    Activations Density 0.021%

    No Known Activations