© 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. 5012
    Prev
    Next
    INDEX
    Explanations

    inquiries or reflections regarding societal issues and personal experiences

    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
    50
    +0.21
    1.0%
    2034
    +0.18
    0.9%
    856
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.21
    0.13
    2034
    +0.18
    0.14
    1150
    +0.09
    0.05
    Negative Logits
    <bos>
    -3.30
     intersper
    -2.01
     fuf
    -1.53
     shenan
    -1.53
     encomp
    -1.52
     depic
    -1.49
     purcha
    -1.43
     reluct
    -1.41
     increa
    -1.37
     snoopy
    -1.36
    POSITIVE LOGITS
     geniales
    0.74
    :
    0.66
    abancı
    0.66
     kutu
    0.63
     kafe
    0.62
     bakteri
    0.62
     kesi
    0.62
     impresionantes
    0.61
     seksi
    0.61
     maravillosas
    0.61
    Activations Density 1.718%

    No Known Activations