© 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. 1703
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names and institutions

    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
    +0.18
    0.7%
    814
    +0.10
    0.4%
    1343
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.18
    0.12
    227
    +0.10
    0.12
    304
    +0.10
    -0.01
    Negative Logits
    <bos>
    -2.71
    ⓧ
    -1.06
    <?
    -0.89
    <?
    
    -0.86
    
    
    -0.86
    /**
    -0.85
    <>
    
    -0.76
    /*
    -0.74
    /*!
    
    -0.74
    /*++
    -0.73
    POSITIVE LOGITS
     fortn
    1.49
     aen
    1.43
     accla
    1.41
     increa
    1.39
     wherea
    1.37
     ?...
    1.37
     eiffel
    1.37
     thut
    1.37
     stockholm
    1.36
     affor
    1.36
    Activations Density 0.992%

    No Known Activations