© 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. 4004
    Prev
    Next
    INDEX
    Explanations

    the word "brush" in various contexts and usages

    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
    0.8%
    50
    +0.15
    0.8%
    1178
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1331
    +0.15
    0.01
    411
    +0.15
    0.01
    889
    +0.14
    0.02
    Negative Logits
    <bos>
    -1.94
    dest
    -0.57
    CD
    -0.55
    Autoritní
    -0.54
     sou
    -0.54
    Anne
    -0.53
    Frank
    -0.53
    Sac
    -0.52
    cd
    -0.51
    dian
    -0.51
    POSITIVE LOGITS
     brush
    1.45
     brushes
    1.37
     bandung
    1.35
     jaya
    1.34
     Brush
    1.33
     Minang
    1.33
    brush
    1.25
     brushing
    1.25
     affor
    1.20
     sovere
    1.20
    Activations Density 0.071%

    No Known Activations