© 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. 6378
    Prev
    Next
    INDEX
    Explanations

    references to different approaches to solving problems or addressing issues

    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
    +0.17
    1.0%
    1407
    +0.14
    0.8%
    397
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1407
    +0.17
    0.03
    370
    +0.14
    0.03
    397
    +0.11
    0.03
    Negative Logits
    <bos>
    -3.33
    ⓧ
    -0.89
    /**
    -0.86
    /***
    -0.81
    /*
    -0.80
    <?
    -0.77
    protected
    -0.75
    ///**
    -0.74
    declare
    -0.71
    public
    -0.68
    POSITIVE LOGITS
     madonna
    1.60
     maroc
    1.58
     stockholm
    1.55
     casio
    1.54
     affor
    1.53
     tupperware
    1.50
     scrat
    1.50
     jurassic
    1.50
     strick
    1.49
     snoopy
    1.49
    Activations Density 0.070%

    No Known Activations