© 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. 10-RES-JB
    11. 2834
    Prev
    Next
    INDEX
    Explanations

    references to player positions and lineup changes in sports

    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
    +0.26
    1.0%
    1842
    +0.10
    0.4%
    736
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1905
    +0.26
    0.06
    823
    +0.10
    0.06
    736
    +0.09
    0.06
    Negative Logits
    <bos>
    -2.08
    /***
    -0.82
    //*/
    -0.75
     /**
    -0.73
    
    -0.73
    ⓧ
    -0.72
     springfox
    -0.72
    contentLoaded
    -0.70
    ///**
    -0.64
    /**
    -0.64
    POSITIVE LOGITS
     keram
    0.94
     silikon
    0.92
     karton
    0.90
     kosme
    0.87
     klap
    0.86
     minimalis
    0.85
     akut
    0.82
     uhr
    0.81
     keramik
    0.81
     defekt
    0.79
    Activations Density 0.510%

    No Known Activations