© 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. 1915
    Prev
    Next
    INDEX
    Explanations

    variations of the word "bump."

    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
    78
    +0.14
    0.8%
    1350
    +0.14
    0.8%
    50
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1350
    +0.14
    0.02
    1363
    +0.14
    0.02
    537
    +0.13
    0.02
    Negative Logits
    <bos>
    -1.87
    <?
    -0.92
    
    -0.89
    /**
    -0.83
    ⓧ
    -0.76
    /*
    -0.69
    /*!
    -0.64
    /***
    -0.64
    Tav
    -0.60
     Tav
    -0.58
    POSITIVE LOGITS
     bump
    1.25
     bumps
    1.19
     bumped
    1.11
     bumping
    1.11
    bump
    1.10
     Bump
    1.09
    bumps
    1.09
    Bump
    0.98
     gubern
    0.90
     LUMP
    0.82
    Activations Density 0.092%

    No Known Activations