© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 3441
    Prev
    Next
    INDEX
    Explanations

    the word "Rat" or variations of it

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1323
    +0.18
    1.0%
    663
    +0.15
    0.8%
    31
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1323
    +0.18
    0.05
    1328
    +0.15
    0.05
    663
    +0.15
    0.05
    Negative Logits
    <bos>
    -1.47
     guma
    -0.59
     kani
    -0.52
     mī
    -0.51
     pinak
    -0.51
     buhay
    -0.51
     excused
    -0.51
     šķ
    -0.50
     tanong
    -0.50
     iyong
    -0.49
    POSITIVE LOGITS
    Rat
    0.94
     Rat
    0.93
     RAT
    0.86
    rat
    0.85
     rat
    0.84
    AT
    0.81
     tat
    0.81
    Rats
    0.80
     Rats
    0.78
     scrat
    0.78
    Activations Density 0.526%

    No Known Activations