© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 4181
    Prev
    Next
    INDEX
    Explanations

    references to discovering or encountering something

    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
    +0.20
    0.7%
    537
    +0.13
    0.5%
    1515
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    537
    +0.20
    0.04
    991
    +0.13
    0.03
    1515
    +0.11
    0.03
    Negative Logits
    <bos>
    -2.33
     allow
    -0.67
    struct
    -0.64
    fill
    -0.64
     protect
    -0.64
     maintain
    -0.63
    for
    -0.63
     allowed
    -0.63
    switch
    -0.63
    AlterField
    -0.63
    POSITIVE LOGITS
     lele
    1.67
     thut
    1.62
     Juf
    1.61
     aen
    1.61
     fua
    1.56
     dises
    1.55
     fta
    1.55
     desir
    1.54
     ftu
    1.53
     meis
    1.53
    Activations Density 0.212%

    No Known Activations