© 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. 3295
    Prev
    Next
    INDEX
    Explanations

    descriptions of technical processes and systems

    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
    +0.34
    1.3%
    1177
    +0.10
    0.4%
    876
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    876
    +0.34
    -0.03
    386
    +0.10
    0.03
    872
    +0.09
    0.07
    Negative Logits
    <bos>
    -1.48
    ///**
    -0.74
     disbur
    -0.68
    ⓧ
    -0.66
    /**
    -0.59
    /***
    -0.56
     defray
    -0.55
    
    -0.53
    habited
    -0.53
    estimable
    -0.52
    POSITIVE LOGITS
     bandung
    1.00
     habet
    0.87
     jawa
    0.87
     haer
    0.77
     jaya
    0.74
     Minang
    0.74
     Hitam
    0.73
     udang
    0.72
     toti
    0.70
     eorum
    0.70
    Activations Density 0.981%

    No Known Activations