© 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. 1163
    Prev
    Next
    INDEX
    Explanations

    references to beads and beadwork

    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
    795
    +0.20
    1.1%
    1937
    +0.18
    1.0%
    1068
    +0.17
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    795
    +0.20
    0.04
    690
    +0.18
    0.04
    1451
    +0.17
    0.04
    Negative Logits
     intersper
    -1.28
     endow
    -0.99
     tolerably
    -0.97
     vainly
    -0.97
     effectually
    -0.96
     gaily
    -0.95
     underval
    -0.93
     lola
    -0.90
     overcrow
    -0.89
     impra
    -0.88
    POSITIVE LOGITS
     beads
    0.80
     bead
    0.75
     barrel
    0.69
    barrel
    0.68
     barrels
    0.65
    igrette
    0.65
     intrig
    0.65
     GRATIS
    0.65
    Bead
    0.64
    beads
    0.63
    Activations Density 0.699%

    No Known Activations