© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 0-RES-JB
    11. 941
    Prev
    Next
    INDEX
    Explanations

    instances of the word "ops."

    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.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    427
    +0.08
    0.2%
    1961
    +0.07
    0.2%
    577
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.08
    0.04
    1927
    +0.07
    0.04
    1363
    +0.07
    0.03
    Negative Logits
    jsoup
    -0.74
    joda
    -0.72
    Iné
    -0.70
    Tetapi
    -0.69
    Související
    -0.67
    Další
    -0.66
     Toutefois
    -0.65
    ését
    -0.65
    Ayrıca
    -0.64
    Alguna
    -0.63
    POSITIVE LOGITS
    ops
    2.29
    OPS
    1.63
    oops
    1.43
     ops
    1.36
    Ops
    1.35
    oped
    1.27
    oping
    1.24
    oop
    1.23
     Ops
    1.19
     oop
    1.10
    Activations Density 0.258%

    No Known Activations