© 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. 1081
    Prev
    Next
    INDEX
    Explanations

    mentions of the specific place "The Trellis"

    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
    1323
    +0.17
    0.9%
    874
    +0.15
    0.8%
    200
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    478
    +0.17
    0.02
    1056
    +0.15
    0.04
    227
    +0.13
    0.05
    Negative Logits
    <bos>
    -1.05
    ghest
    -0.64
     intptr
    -0.63
    ;%%
    -0.56
    mstyle
    -0.54
    yarnpkg
    -0.53
    CPF
    -0.53
    Autor
    -0.53
    אבל
    -0.52
    WithMany
    -0.51
    POSITIVE LOGITS
     Tre
    1.21
     TRE
    1.19
     fta
    1.10
    Tre
    1.04
     Trek
    1.04
     Trekking
    1.03
    Trek
    0.99
     malheure
    0.97
     aen
    0.97
     squa
    0.97
    Activations Density 0.577%

    No Known Activations