© 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. 481
    Prev
    Next
    INDEX
    Explanations

    instances of social media reactions and public responses

    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
    +0.34
    1.3%
    198
    +0.14
    0.5%
    1150
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    669
    +0.34
    0.08
    198
    +0.14
    0.07
    482
    +0.11
    0.04
    Negative Logits
    <bos>
    -2.81
     /**
    
    -0.66
    /***
    
    -0.61
    LayoutStyle
    -0.53
    Xoxo
    -0.52
    Попис
    -0.51
     biodivers
    -0.51
    ⓧ
    -0.50
    CodeAttribute
    -0.50
    //...
    -0.49
    POSITIVE LOGITS
     accla
    1.17
     Khart
    1.07
     Czechos
    1.04
     Juf
    1.04
     Fulda
    1.03
     Keny
    1.01
     Minang
    1.00
     maneu
    0.99
     fortn
    0.97
     inev
    0.97
    Activations Density 1.172%

    No Known Activations