© 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. 34
    Prev
    Next
    INDEX
    Explanations

    references to political parties, particularly the Democratic and Republican parties

    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
    1.5%
    1870
    +0.10
    0.6%
    1271
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    549
    +0.27
    0.04
    1065
    +0.10
    0.04
    1404
    +0.10
    0.03
    Negative Logits
    <bos>
    -3.00
    <?
    -0.83
    ⓧ
    -0.76
    
    -0.76
    <?
    -0.66
    /***
    -0.65
     consultato
    -0.65
     inaugurate
    -0.64
     evacuate
    -0.63
     modulate
    -0.63
    POSITIVE LOGITS
     Minang
    1.14
     véhic
    1.09
     Khart
    1.07
     Jambi
    1.05
     Batam
    1.02
    Fitment
    1.01
     bandung
    1.01
     party
    0.99
     Party
    0.98
     Mérida
    0.98
    Activations Density 0.047%

    No Known Activations