© 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. 166
    Prev
    Next
    INDEX
    Explanations

    information related to tides and water levels

    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
    204
    +0.09
    0.3%
    871
    +0.08
    0.3%
    1271
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    204
    +0.09
    0.02
    388
    +0.08
    0.02
    690
    +0.07
    0.02
    Negative Logits
    <bos>
    -1.35
     AssemblyCompany
    -0.81
    /**
    -0.70
    ArgumentParser
    -0.67
    AutoresizingMask
    -0.66
     alko
    -0.65
    addComponent
    -0.64
     erk
    -0.64
    TestTools
    -0.64
    بوابة
    -0.63
    POSITIVE LOGITS
     tide
    2.26
     tides
    2.10
     ecru
    1.64
     Tides
    1.59
     Tide
    1.50
     tupperware
    1.47
    Tide
    1.40
     swarovski
    1.38
     hairc
    1.38
     bandeau
    1.32
    Activations Density 0.147%

    No Known Activations