© 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. 6-RES-JB
    11. 6996
    Prev
    Next
    INDEX
    Explanations

    sports league-related terms

    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.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.17
    1.1%
    805
    +0.12
    0.8%
    1562
    +0.10
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    805
    +0.17
    0.03
    156
    +0.12
    0.03
    1562
    +0.10
    0.03
    Negative Logits
    <bos>
    -3.32
    /***
    -0.82
     AssemblyCompany
    -0.81
     springfox
    -0.67
    لينكات
    -0.67
     propOrder
    -0.63
    //---
    -0.63
    Unmarshaller
    -0.63
    displayquote
    -0.61
    RTEX
    -0.61
    POSITIVE LOGITS
     riviera
    1.42
     maroc
    1.41
     rafra
    1.36
     véhic
    1.36
     Juf
    1.36
     quoique
    1.35
     Confe
    1.35
     indestru
    1.34
     Minang
    1.32
     soulign
    1.30
    Activations Density 0.067%

    No Known Activations