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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 586
    Prev
    Next
    INDEX
    Explanations

    the presence of the term "Tra" in various forms, likely indicating a focus on tracking or tracing features associated with that term

    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
    31
    +0.15
    0.9%
    50
    +0.15
    0.9%
    406
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    31
    +0.15
    0.02
    1622
    +0.15
    0.02
    404
    +0.14
    0.02
    Negative Logits
    <bos>
    -2.29
     AssemblyCompany
    -0.61
    /*!
    
    -0.61
    /***
    
    -0.61
    
    
    -0.57
     come
    -0.55
    ⓧ
    -0.54
    else
    -0.53
    //---
    -0.52
    /**
    -0.52
    POSITIVE LOGITS
     Tra
    1.31
    Tra
    1.15
     traktor
    1.11
     Minang
    1.11
     tra
    1.09
     Keny
    1.06
     Karang
    1.05
     Jambi
    1.05
     TRA
    1.03
     Banjar
    1.02
    Activations Density 0.074%

    No Known Activations