© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 2877
    Prev
    Next
    INDEX
    Explanations

    locations, specifically related to New York City

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    161
    +0.10
    0.3%
    1416
    +0.07
    0.2%
    1940
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1896
    +0.10
    0.02
    1120
    +0.07
    0.03
    443
    +0.07
    0.02
    Negative Logits
    
    -0.68
    })();
    -0.65
    <?
    -0.62
    /***
    -0.58
    <bos>
    -0.57
     invade
    -0.55
    industan
    -0.53
    municipi
    -0.53
     inaugurate
    -0.53
    estimable
    -0.52
    POSITIVE LOGITS
     NYC
    1.29
    NYC
    1.28
     nyc
    1.23
     lamborghini
    1.05
     ducati
    1.04
     stockholm
    0.97
     mitsubishi
    0.96
     bosch
    0.95
     chrysler
    0.95
     stihl
    0.95
    Activations Density 0.208%

    No Known Activations