© 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. 923
    Prev
    Next
    INDEX
    Explanations

    ingredients and cooking instructions related to a recipe that includes bacon

    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
    298
    +0.11
    0.4%
    390
    +0.11
    0.4%
    976
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1120
    +0.11
    0.05
    1252
    +0.11
    0.04
    683
    +0.10
    0.04
    Negative Logits
     mit
    -0.69
    TORE
    -0.66
     get
    -0.66
     måske
    -0.62
     복
    -0.61
    YTE
    -0.61
     hold
    -0.61
     chăm
    -0.61
     muligt
    -0.60
    ,
    -0.60
    POSITIVE LOGITS
     Sinal
    1.77
     Juf
    1.61
     aen
    1.61
     wherea
    1.60
     ricardo
    1.56
     Áng
    1.56
     ftu
    1.54
     Khart
    1.54
     secon
    1.52
     alberto
    1.52
    Activations Density 0.272%

    No Known Activations