© 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. 1505
    Prev
    Next
    INDEX
    Explanations

    numeric values or codes related to products or specifications

    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
    +0.22
    1.0%
    1978
    +0.17
    0.8%
    276
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1978
    +0.22
    0.07
    1597
    +0.17
    0.03
    994
    +0.10
    0.02
    Negative Logits
    <bos>
    -2.62
    ⓧ
    -0.77
     rehabilitate
    -0.77
    /***
    
    -0.75
     springfox
    -0.72
     amass
    -0.71
     banish
    -0.70
    /**
    -0.69
    ///**
    -0.69
     modernize
    -0.69
    POSITIVE LOGITS
     maroc
    0.87
     soggior
    0.86
     corrom
    0.83
     bunda
    0.82
     fernando
    0.81
     monaster
    0.81
     Momb
    0.80
    cdon
    0.80
    orsche
    0.79
     silikon
    0.78
    Activations Density 0.133%

    No Known Activations