© 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
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 4494
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "restaurant" and its variations

    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
    +0.27
    1.5%
    1677
    +0.11
    0.6%
    1964
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1590
    +0.27
    0.02
    1013
    +0.11
    0.02
    1677
    +0.11
    0.02
    Negative Logits
    <bos>
    -2.57
    ⓧ
    -1.05
    <?
    -0.86
    
    -0.82
    /**
    -0.80
    <?
    -0.77
    /***
    -0.75
     disbur
    -0.74
     endow
    -0.69
    Искәрмәләр
    -0.67
    POSITIVE LOGITS
     restaurant
    1.14
     Restaurant
    1.05
    Restaurant
    1.03
    restaurant
    0.99
     restaurants
    0.95
     Restaurants
    0.92
    Restaurants
    0.91
     Jambi
    0.86
     éto
    0.84
     pleins
    0.82
    Activations Density 0.030%

    No Known Activations