© 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. 1545
    Prev
    Next
    INDEX
    Explanations

    expressions of dependency and the need for support

    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
    1.1%
    32
    +0.11
    0.4%
    1363
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1103
    +0.28
    0.05
    67
    +0.11
    0.04
    1129
    +0.10
    0.05
    Negative Logits
    <bos>
    -2.22
    ⓧ
    -0.73
    /***
    -0.69
    /*
    -0.64
    /**
    -0.61
    fileprivate
    -0.60
    //---
    -0.60
    /*@
    -0.57
    Съ
    -0.55
     darted
    -0.54
    POSITIVE LOGITS
     bandung
    1.08
     Keny
    1.05
     strass
    1.05
    !!</
    1.00
     tramont
    1.00
     lele
    0.99
     hunde
    0.98
     shopee
    0.97
     cannes
    0.96
     LIRE
    0.96
    Activations Density 0.146%

    No Known Activations