© 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. 1172
    Prev
    Next
    INDEX
    Explanations

    mentions of business strategies or plans

    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
    +0.10
    0.4%
    1870
    +0.08
    0.3%
    555
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1789
    +0.10
    0.05
    1485
    +0.08
    0.04
    626
    +0.08
    0.03
    Negative Logits
    <bos>
    -1.58
    /***
    -0.86
    
    -0.80
    ⓧ
    -0.80
    <?
    -0.78
    /**
    -0.69
    displayquote
    -0.67
    <?
    -0.66
    /*++
    -0.65
    ///**
    -0.64
    POSITIVE LOGITS
     strategy
    2.06
     Strategy
    1.90
    strategy
    1.86
     strategies
    1.78
     strategia
    1.76
     STRATEGY
    1.72
    Strategy
    1.70
    strategies
    1.64
     Strategies
    1.63
     strategie
    1.51
    Activations Density 0.103%

    No Known Activations