© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 2742
    Prev
    Next
    INDEX
    Explanations

    references to real-life stories or individuals in media

    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
    +0.27
    1.0%
    198
    +0.18
    0.7%
    1842
    +0.18
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.27
    0.08
    872
    +0.18
    0.07
    227
    +0.18
    0.07
    Negative Logits
    <bos>
    -2.73
     nahilalakip
    -0.88
     chi̍t
    -0.88
     initComponents
    -0.87
    AsUp
    -0.86
    RegressionTest
    -0.85
     EconPapers
    -0.84
    Autoritní
    -0.83
    addComponent
    -0.82
    SequentialGroup
    -0.81
    POSITIVE LOGITS
     affor
    2.34
     increa
    2.28
     Juf
    2.21
     disagre
    2.18
     impra
    2.08
     reluct
    2.07
     fuf
    2.04
     unspeak
    1.97
     maneu
    1.95
     inconce
    1.95
    Activations Density 0.768%

    No Known Activations