© 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. 327
    Prev
    Next
    INDEX
    Explanations

    references to violence and its implications

    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
    +0.24
    1.1%
    1535
    +0.21
    1.0%
    50
    +0.16
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1535
    +0.24
    0.07
    2019
    +0.21
    0.08
    1445
    +0.16
    0.07
    Negative Logits
    <bos>
    -1.50
    ⓧ
    -1.46
    /**
    -1.22
    
    -1.21
    /***
    -1.12
    <?
    -1.10
     springfox
    -1.08
     courtier
    -0.92
    ///**
    -0.92
     schoolmaster
    -0.88
    POSITIVE LOGITS
    ↵↵
    0.63
    ↵
    0.52
    ↵↵↵
    0.51
    <eos>
    0.51
     atmosfera
    0.50
     marea
    0.50
     But
    0.48
     A
    0.48
     moza
    0.48
    But
    0.47
    Activations Density 0.257%

    No Known Activations