© 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. 0-RES-JB
    11. 2554
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to doing multiple things at the same time

    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
    814
    +0.08
    0.3%
    1717
    +0.08
    0.2%
    1602
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1717
    +0.08
    0.02
    344
    +0.08
    0.02
    1649
    +0.07
    0.02
    Negative Logits
    echo
    -0.74
    落
    -0.73
     ask
    -0.73
    case
    -0.72
    再
    -0.72
    문
    -0.71
     assume
    -0.71
    //
    -0.70
    ب
    -0.70
    throw
    -0.70
    POSITIVE LOGITS
     Simultaneous
    2.63
     Simult
    2.61
    simult
    2.60
     simultaneous
    2.56
     guarante
    2.52
     Simultaneously
    2.50
     stockholm
    2.48
    Simult
    2.47
     fta
    2.42
     wien
    2.41
    Activations Density 0.177%

    No Known Activations