© 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. 4021
    Prev
    Next
    INDEX
    Explanations

    information related to academia, advising, academic programs, and university requirements

    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
    +0.23
    0.9%
    738
    +0.11
    0.4%
    297
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1063
    +0.23
    0.06
    1903
    +0.11
    0.06
    792
    +0.08
    0.06
    Negative Logits
    <bos>
    -2.37
     springfox
    -0.72
    MarshalTo
    -0.71
    PerformLayout
    -0.70
    HasIndex
    -0.69
    /*
    -0.62
    ValueGenerated
    -0.62
    ///**
    -0.62
     mergeFrom
    -0.61
    ISupport
    -0.61
    POSITIVE LOGITS
     Minang
    1.59
     accla
    1.48
     affor
    1.46
     saar
    1.42
     wien
    1.39
     maneu
    1.38
     kano
    1.38
     lidl
    1.34
     silikon
    1.33
     lele
    1.32
    Activations Density 0.836%

    No Known Activations