© 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
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 1536
    Prev
    Next
    INDEX
    Explanations

    phrases related to sitting or positioning

    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
    +0.23
    1.2%
    1671
    +0.13
    0.7%
    1323
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1671
    +0.23
    0.03
    1323
    +0.13
    0.03
    370
    +0.11
    0.03
    Negative Logits
    <bos>
    -2.35
    РЭ
    -0.59
     komp
    -0.55
     darbu
    -0.55
    verifyException
    -0.51
    public
    -0.49
     inform
    -0.49
     advance
    -0.49
    do
    -0.49
     declare
    -0.48
    POSITIVE LOGITS
     unlaw
    1.08
     sit
    1.05
     sitting
    1.05
     despotism
    1.04
     Sit
    1.04
     Sitting
    1.03
    Sit
    1.02
    sitting
    1.00
     pollut
    0.98
    dirond
    0.98
    Activations Density 0.052%

    No Known Activations