© 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. 3130
    Prev
    Next
    INDEX
    Explanations

    references to a specific person named Michelle

    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
    411
    +0.15
    0.9%
    874
    +0.15
    0.8%
    331
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1097
    +0.15
    0.04
    227
    +0.15
    0.03
    1741
    +0.12
    0.00
    Negative Logits
    <bos>
    -1.48
    bolista
    -0.64
    webElementXpaths
    -0.60
     الرياضيه
    -0.60
    ząd
    -0.55
     initWithFrame
    -0.55
    Perd
    -0.54
    Ответ
    -0.54
    Norman
    -0.54
    ParallelGroup
    -0.52
    POSITIVE LOGITS
     michelle
    1.37
     impra
    1.16
     Michelle
    1.10
     Czechos
    1.06
     stockholm
    1.05
    Michelle
    1.03
     Khart
    1.03
     scrat
    1.00
     madonna
    1.00
     Somal
    1.00
    Activations Density 0.187%

    No Known Activations