© 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. 548
    Prev
    Next
    INDEX
    Explanations

    sentences that contain factual statements or conclusions

    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
    +0.30
    1.5%
    382
    +0.20
    1.0%
    2019
    +0.16
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.30
    0.17
    2034
    +0.20
    0.14
    1535
    +0.16
    0.11
    Negative Logits
    <bos>
    -2.12
    ⓧ
    -1.19
    /**
    -1.18
     springfox
    -0.99
    <?
    -0.99
    /***
    -0.97
    ///**
    -0.97
    /*
    -0.95
    
    -0.87
    Transkript
    -0.79
    POSITIVE LOGITS
     It
    0.73
     Putih
    0.70
     There
    0.67
     This
    0.67
     Although
    0.67
     The
    0.65
     They
    0.65
     épu
    0.64
     When
    0.62
     Its
    0.62
    Activations Density 0.886%

    No Known Activations