© 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
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 499
    Prev
    Next
    INDEX
    Explanations

    references to cities

    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
    +0.28
    1.6%
    1178
    +0.10
    0.6%
    390
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    220
    +0.28
    0.04
    390
    +0.10
    0.04
    437
    +0.09
    0.04
    Negative Logits
    <bos>
    -2.87
    
    -0.94
    <?
    -0.84
     intersper
    -0.84
    /**
    -0.82
     defray
    -0.77
    ⓧ
    -0.73
     harmonize
    -0.73
     rehabilitate
    -0.72
    /*
    -0.72
    POSITIVE LOGITS
     city
    1.08
    city
    0.91
     keramik
    0.89
    City
    0.88
     City
    0.87
     Schrö
    0.86
     Cidade
    0.84
     catég
    0.84
     churrasco
    0.84
     cities
    0.84
    Activations Density 0.052%

    No Known Activations