© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 84
    Prev
    Next
    INDEX
    Explanations

    terms associated with the act of removing or taking away

    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
    +0.27
    1.5%
    1328
    +0.10
    0.6%
    1392
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    61
    +0.27
    0.03
    1328
    +0.10
    0.02
    1950
    +0.10
    0.02
    Negative Logits
    <bos>
    -2.86
    ⓧ
    -0.88
    /***
    
    -0.81
    
    
    -0.77
    <?
    -0.76
    //*/
    -0.71
    ///**
    -0.70
    /**
    -0.66
    class
    -0.65
    <?
    
    -0.62
    POSITIVE LOGITS
     lele
    1.33
     bandung
    1.29
     jaya
    1.28
     sentra
    1.26
     dises
    1.25
     pank
    1.23
     kac
    1.22
     jawa
    1.21
     salat
    1.19
     wien
    1.18
    Activations Density 0.073%

    No Known Activations