© 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. 2166
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistical information

    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
    +0.17
    0.7%
    1343
    +0.15
    0.6%
    1699
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    924
    +0.17
    0.03
    1343
    +0.15
    0.03
    1804
    +0.10
    0.03
    Negative Logits
    <bos>
    -1.79
     intersper
    -1.54
    ⓧ
    -1.28
    
    -1.23
     indestru
    -1.20
    /**
    -1.18
    <?
    -1.17
     shenan
    -1.12
     overcrow
    -1.08
     encomp
    -1.08
    POSITIVE LOGITS
     Kategor
    0.74
    *</
    0.70
     cosmé
    0.67
     orale
    0.62
     elef
    0.62
     vitale
    0.61
     utensi
    0.61
     alfabe
    0.61
     mentale
    0.60
     magis
    0.59
    Activations Density 0.039%

    No Known Activations