© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 0-RES-JB
    11. 372
    Prev
    Next
    INDEX
    Explanations

    words related to a specific location, specifically the downtown area of a city

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.07
    0.3%
    1034
    +0.07
    0.2%
    161
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1485
    +0.07
    0.03
    1013
    +0.07
    0.03
    579
    +0.07
    0.02
    Negative Logits
    ⓧ
    -0.91
    
    -0.89
    /*
    -0.87
    /**
    -0.86
    <?
    -0.81
    /*++
    -0.74
    <?
    -0.71
    #
    -0.70
     enable
    -0.68
    //{
    -0.68
    POSITIVE LOGITS
     downtown
    2.05
     Downtown
    1.99
    downtown
    1.98
    Downtown
    1.97
     aen
    1.78
     maneu
    1.66
     fup
    1.65
     impra
    1.65
     inev
    1.64
     levis
    1.64
    Activations Density 0.117%

    No Known Activations