© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 256
    Prev
    Next
    INDEX
    Explanations

    mentions and references to the Trump administration

    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
    +0.24
    1.0%
    1178
    +0.09
    0.4%
    1741
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1178
    +0.24
    0.07
    1364
    +0.09
    0.05
    817
    +0.08
    0.05
    Negative Logits
    <bos>
    -2.47
    <?
    
    -0.77
    /***
    
    -0.72
    
    
    -0.65
    ⓧ
    -0.62
    /**
    -0.60
     locate
    -0.59
     relocate
    -0.57
     evolve
    -0.57
     gather
    -0.57
    POSITIVE LOGITS
     Bibl
    1.26
     Khart
    1.24
     bayern
    1.23
     riva
    1.22
     Minang
    1.18
     hcm
    1.15
     frankfurt
    1.14
     mef
    1.13
     valencia
    1.12
     Keny
    1.10
    Activations Density 0.110%

    No Known Activations