© 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. 76
    Prev
    Next
    INDEX
    Explanations

    references to payments and financial transactions

    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
    +0.25
    1.2%
    241
    +0.11
    0.5%
    1035
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1129
    +0.25
    0.05
    1351
    +0.11
    0.04
    1035
    +0.10
    0.04
    Negative Logits
    <bos>
    -2.54
    CommonModule
    -0.63
     dras
    -0.60
    proc
    -0.56
     erk
    -0.56
    //----
    -0.55
     rek
    -0.55
     vun
    -0.55
    mainAxisSize
    -0.55
     rekon
    -0.55
    POSITIVE LOGITS
     maneu
    1.42
     disagre
    1.37
     chrysler
    1.31
     milf
    1.28
     🤣🤣
    1.26
     impra
    1.25
     unspeak
    1.24
     stockholm
    1.24
     shenan
    1.24
     excru
    1.23
    Activations Density 0.133%

    No Known Activations