© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 5971
    Prev
    Next
    INDEX
    Explanations

    conditional statements beginning with "if" and "even if"

    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.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.25
    1.1%
    890
    +0.08
    0.4%
    1370
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1652
    +0.25
    0.03
    1370
    +0.08
    0.04
    1643
    +0.08
    0.04
    Negative Logits
    <bos>
    -2.39
    /*
    -0.78
    <?
    -0.76
    /***
    -0.76
    
    -0.69
    ⓧ
    -0.62
    /**
    -0.61
     AssemblyCompany
    -0.61
    public
    -0.59
    ///**
    -0.57
    POSITIVE LOGITS
     wien
    1.41
     ftu
    1.39
     fup
    1.32
     perfon
    1.31
     fta
    1.31
     thut
    1.30
     fays
    1.27
     aen
    1.27
     maneu
    1.27
     Manufact
    1.26
    Activations Density 0.213%

    No Known Activations