© 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. 1034
    Prev
    Next
    INDEX
    Explanations

    prepositions and conjunctions commonly used in written text

    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
    +0.20
    0.7%
    1045
    +0.09
    0.3%
    446
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    446
    +0.20
    0.05
    1776
    +0.09
    0.05
    1873
    +0.08
    0.05
    Negative Logits
    <bos>
    -2.99
    .
    -0.99
    ,
    -0.95
    ;
    -0.87
      
    -0.76
     to
    -0.76
     is
    -0.74
    ↵
    -0.72
    。
    -0.72
    ).
    -0.72
    POSITIVE LOGITS
     dises
    1.74
     fta
    1.70
     nece
    1.68
     Minang
    1.67
     ftu
    1.66
     lidl
    1.65
     bandung
    1.65
     increa
    1.65
     inev
    1.63
     wien
    1.62
    Activations Density 0.792%

    No Known Activations