© 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. 6-RES-JB
    11. 7964
    Prev
    Next
    INDEX
    Explanations

    the word "swing" or mentions of swinging a club or baseball bat

    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
    597
    +0.14
    0.7%
    1045
    +0.14
    0.7%
    1491
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    597
    +0.14
    0.03
    1935
    +0.14
    0.02
    690
    +0.12
    0.02
    Negative Logits
    <bos>
    -2.32
    /*
    -0.79
    <tfoot>
    -0.76
    ⓧ
    -0.70
    ///**
    -0.70
    typeorm
    -0.69
    HasOne
    -0.68
    lateinit
    -0.68
    /***
    -0.67
    RuleContext
    -0.63
    POSITIVE LOGITS
     increa
    1.61
     stockholm
    1.59
     affor
    1.53
     wherea
    1.50
     unden
    1.46
     strick
    1.44
     disagre
    1.44
     impra
    1.42
     unce
    1.42
     fta
    1.42
    Activations Density 0.193%

    No Known Activations