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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 532
    Prev
    Next
    INDEX
    Explanations

    references to criminal charges and legal proceedings

    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
    2019
    +0.32
    1.8%
    50
    +0.26
    1.5%
    1535
    +0.21
    1.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2019
    +0.32
    0.14
    1535
    +0.26
    0.12
    304
    +0.21
    0.03
    Negative Logits
    <bos>
    -2.37
    ⓧ
    -1.27
    /***
    -1.13
    /**
    -1.05
    
    -0.97
    ///**
    -0.96
    <?
    -0.96
     springfox
    -0.94
    /*
    -0.87
    requently
    -0.84
    POSITIVE LOGITS
     unspeak
    1.18
     accla
    1.12
     apprehen
    1.05
     Juf
    1.03
     affor
    1.02
     intrigu
    1.01
     indescri
    0.99
     maneu
    0.98
     uninten
    0.96
     soulign
    0.96
    Activations Density 0.442%

    No Known Activations