© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 215
    Prev
    Next
    INDEX
    Explanations

    phrases related to watching videos or trailers

    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
    +0.28
    1.0%
    453
    +0.10
    0.4%
    1577
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.28
    0.04
    1309
    +0.10
    0.03
    441
    +0.10
    0.03
    Negative Logits
    <bos>
    -2.61
    ⓧ
    -1.07
    /**
    -0.95
    /***
    -0.91
    /*
    -0.89
    <?
    -0.85
    
    -0.85
    /*++
    -0.76
    WebElementEntity
    -0.74
    <?
    -0.71
    POSITIVE LOGITS
     maneu
    1.21
     affor
    1.16
     accla
    1.09
     disreg
    1.07
     inev
    1.06
     practition
    1.05
     depic
    1.05
     erad
    1.01
     indescri
    1.01
     disgra
    1.01
    Activations Density 0.126%

    No Known Activations