© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 334
    Prev
    Next
    INDEX
    Explanations

    specific biochemical compounds and related terminology

    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
    1842
    +0.14
    0.5%
    50
    +0.12
    0.4%
    453
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.14
    0.09
    1842
    +0.12
    0.04
    227
    +0.10
    0.07
    Negative Logits
    <bos>
    -3.10
     for
    -0.83
     mergeFrom
    -0.83
     put
    -0.80
      
    -0.80
    ,
    -0.80
    برای
    -0.79
     betweenstory
    -0.79
     is
    -0.78
        
    -0.78
    POSITIVE LOGITS
     maneu
    2.68
     affor
    2.62
     increa
    2.60
     scrat
    2.55
     accla
    2.49
     wherea
    2.49
     reluct
    2.49
     excru
    2.48
     milf
    2.45
     shenan
    2.42
    Activations Density 0.700%

    No Known Activations