© 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. 57
    Prev
    Next
    INDEX
    Explanations

    references to the city of Rio de Janeiro

    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
    2011
    +0.19
    1.0%
    1103
    +0.16
    0.8%
    1350
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1052
    +0.19
    0.02
    1056
    +0.16
    0.02
    227
    +0.15
    0.02
    Negative Logits
     shuddered
    -0.73
     hastened
    -0.69
     mī
    -0.64
     ļ
    -0.64
     darted
    -0.63
     mustered
    -0.63
    <bos>
    -0.62
     ģ
    -0.62
     shivered
    -0.62
     liel
    -0.61
    POSITIVE LOGITS
     Rio
    1.59
    Rio
    1.55
     RIO
    1.10
    Plasma
    1.10
     Plasma
    1.06
     plasma
    1.04
    plasma
    0.99
    RIO
    0.97
     rio
    0.96
     Traité
    0.80
    Activations Density 0.133%

    No Known Activations