© 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. 10-RES-JB
    11. 3134
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to inquiries or tips for information

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    394
    +0.23
    1.2%
    856
    +0.18
    1.0%
    453
    +0.17
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    453
    +0.23
    0.13
    856
    +0.18
    0.05
    1343
    +0.17
    0.11
    Negative Logits
    <bos>
    -2.58
    .
    -0.83
    ↵↵
    -0.77
    ...
    -0.75
    ↵
    -0.70
    …
    -0.70
     ...
    -0.70
      
    -0.69
    ↵↵↵
    -0.68
    !
    -0.67
    POSITIVE LOGITS
     lamborghini
    1.47
     sappi
    1.46
     Minang
    1.39
     peugeot
    1.38
     Khart
    1.33
     nece
    1.32
     suspic
    1.31
     viciss
    1.31
     coö
    1.30
     tramont
    1.28
    Activations Density 2.259%

    No Known Activations