© 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. 0-RES-JB
    11. 1711
    Prev
    Next
    INDEX
    Explanations

    mentions of medical procedures, injuries, and surgeries related to the shoulder

    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
    889
    +0.10
    0.3%
    90
    +0.08
    0.3%
    1520
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    128
    +0.10
    0.03
    1633
    +0.08
    0.03
    889
    +0.08
    0.03
    Negative Logits
    ⓧ
    -0.75
    
    -0.73
    <?
    -0.66
    /***
    -0.63
    /**
    -0.63
    ///**
    -0.56
    #
    -0.56
    /*
    -0.56
     diversify
    -0.55
    <?
    -0.55
    POSITIVE LOGITS
     shoulder
    2.65
     Shoulder
    2.42
     shoulders
    2.39
    shoulder
    2.35
    Shoulder
    2.18
     Shoulders
    1.98
     aen
    1.19
     stockholm
    1.18
     ibiza
    1.18
     lidl
    1.15
    Activations Density 0.114%

    No Known Activations