© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 5125
    Prev
    Next
    INDEX
    Explanations

    key terms related to essential elements or fundamentals in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    words related to key components or foundational elements

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    1127
    +0.15
    0.7%
    1363
    +0.12
    0.6%
    50
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.15
    0.06
    1870
    +0.12
    0.04
    990
    +0.12
    0.05
    Negative Logits
    <bos>
    -2.20
     solidar
    -0.87
    /***
    -0.79
     desinf
    -0.72
     ideolog
    -0.70
    Vanjske
    -0.70
    /*!
    -0.68
     impon
    -0.68
    //---
    -0.64
     /**
    -0.64
    POSITIVE LOGITS
     impra
    1.48
     unspeak
    1.44
     unwarran
    1.36
     tolerably
    1.33
     ecru
    1.31
     inappro
    1.30
     snoopy
    1.27
     gaily
    1.26
     indescri
    1.24
     outlander
    1.23
    Activations Density 0.421%

    No Known Activations