© 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. 1489
    Prev
    Next
    INDEX
    Explanations

    numbers and measurements relating to quantities and amounts

    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
    +0.29
    1.2%
    478
    +0.14
    0.6%
    198
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    776
    +0.29
    0.06
    198
    +0.14
    0.05
    143
    +0.12
    0.05
    Negative Logits
    <bos>
    -2.56
    ⓧ
    -0.82
    /***
    -0.66
    beforeAll
    -0.64
     chi̍t
    -0.63
    Autoritní
    -0.62
    <?
    -0.61
    ///**
    -0.61
     jadx
    -0.59
     /**
    -0.58
    POSITIVE LOGITS
     bandung
    1.19
     jaya
    1.06
     lele
    1.06
     Minang
    1.05
     Nusantara
    1.01
     jati
    0.99
     maneu
    0.98
     unlaw
    0.98
     Karang
    0.97
     jawa
    0.97
    Activations Density 0.129%

    No Known Activations