© 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. 1546
    Prev
    Next
    INDEX
    Explanations

    descriptions of security measures and their contexts

    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
    +0.28
    1.1%
    1499
    +0.10
    0.4%
    924
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1216
    +0.28
    0.07
    946
    +0.10
    0.05
    1499
    +0.10
    0.07
    Negative Logits
    <bos>
    -1.69
    ⓧ
    -0.91
    /***
    -0.68
    ///**
    -0.62
     BECOME
    -0.62
     otu
    -0.61
     betweenstory
    -0.60
     sguardo
    -0.59
     kule
    -0.58
    versations
    -0.56
    POSITIVE LOGITS
     McLaugh
    1.12
     philanth
    1.10
     aussitôt
    1.08
     spécialement
    1.07
     Vaugh
    1.04
     pamph
    1.00
     shenan
    0.99
     Middles
    0.97
     sophistic
    0.96
     McInt
    0.95
    Activations Density 0.552%

    No Known Activations