© 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. 0-RES-JB
    11. 1753
    Prev
    Next
    INDEX
    Explanations

    mentions of corporate security measures and protocols

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.09
    0.4%
    1870
    +0.07
    0.3%
    1334
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    978
    +0.09
    0.04
    1918
    +0.07
    0.04
    1915
    +0.07
    0.03
    Negative Logits
    <bos>
    -1.04
    ⓧ
    -0.91
    
    -0.87
    /**
    -0.85
    <?
    -0.73
    <?
    -0.69
    /*
    -0.68
    /***
    -0.67
    }{||
    -0.59
    ValueGenerated
    -0.58
    POSITIVE LOGITS
     corporate
    2.05
     Corporate
    1.99
    Corporate
    1.93
    corporate
    1.77
     CORPOR
    1.59
     Juf
    1.51
     corpor
    1.27
     Minang
    1.21
    CORPOR
    1.21
     applau
    1.21
    Activations Density 0.146%

    No Known Activations