© 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. 8703
    Prev
    Next
    INDEX
    Explanations

    terms related to academic research and conferences

    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
    1842
    +0.16
    0.8%
    50
    +0.15
    0.7%
    1150
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1870
    +0.16
    0.09
    227
    +0.15
    0.17
    1842
    +0.13
    0.07
    Negative Logits
    <bos>
    -3.41
    MarshalTo
    -0.79
    /***
    -0.75
    //---
    -0.72
     onStop
    -0.72
    PerformLayout
    -0.68
    HasIndex
    -0.68
    /**
    -0.68
    }{||
    -0.67
    protected
    -0.66
    POSITIVE LOGITS
     maneu
    1.77
     increa
    1.73
     impra
    1.71
     affor
    1.71
     reluct
    1.66
     disagre
    1.60
     excru
    1.59
     inev
    1.59
     Minang
    1.58
     accla
    1.57
    Activations Density 3.333%

    No Known Activations