© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 2208
    Prev
    Next
    INDEX
    Explanations

    mentions of grocery stores

    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
    783
    +0.08
    0.3%
    1013
    +0.07
    0.2%
    1407
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1013
    +0.08
    0.03
    838
    +0.07
    0.02
    465
    +0.06
    0.02
    Negative Logits
    <bos>
    -1.30
     Randy
    -0.55
    amaño
    -0.54
    <!--
    
    -0.51
    /**
    -0.51
    lugin
    -0.50
     vernie
    -0.50
    ыре
    -0.49
    afterEach
    -0.49
    //---
    -0.49
    POSITIVE LOGITS
     grocery
    1.94
    Grocery
    1.62
     Grocery
    1.61
     groceries
    1.60
     supermarket
    1.60
    grocery
    1.57
     grocer
    1.45
     Supermarket
    1.34
     bandung
    1.28
     supermarkets
    1.27
    Activations Density 0.065%

    No Known Activations