© 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. 4784
    Prev
    Next
    INDEX
    Explanations

    statements made by politicians or public figures

    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
    +0.30
    1.2%
    453
    +0.09
    0.3%
    604
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    888
    +0.30
    0.07
    617
    +0.09
    0.06
    247
    +0.08
    0.06
    Negative Logits
    <bos>
    -2.66
     intersper
    -2.21
     encomp
    -2.10
     quitted
    -1.80
     inconce
    -1.62
     overcrow
    -1.62
     suscep
    -1.62
     reluct
    -1.60
     indestru
    -1.60
     disagre
    -1.59
    POSITIVE LOGITS
    BorderLayout
    0.66
    AttributeSet
    0.64
     "
    0.63
     “
    0.62
    JTable
    0.60
    ]=="
    0.60
    JsonResponse
    0.59
    BeanUtils
    0.57
    QtWidgets
    0.57
    UIColor
    0.56
    Activations Density 0.542%

    No Known Activations