© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 678
    Prev
    Next
    INDEX
    Explanations

    references to a specific event or competition called "MotoGP."

    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
    1506
    +0.13
    0.4%
    101
    +0.10
    0.3%
    1306
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.13
    0.03
    690
    +0.10
    0.03
    1506
    +0.09
    0.03
    Negative Logits
    queryInterface
    -0.78
    EndProject
    -0.67
     CWE
    -0.66
    <bos>
    -0.64
    <?
    -0.64
     <",
    -0.63
    GORITH
    -0.62
    zonych
    -0.62
     Shetterly
    -0.62
    /**
    -0.61
    POSITIVE LOGITS
     GP
    2.03
    GP
    1.70
     impra
    1.67
     GPs
    1.63
     affor
    1.60
     gp
    1.56
     guarante
    1.54
     maneu
    1.49
     tupperware
    1.48
     increa
    1.46
    Activations Density 0.300%

    No Known Activations