© 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. 6-RES-JB
    11. 2323
    Prev
    Next
    INDEX
    Explanations

    references to sports matches and statistics

    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
    1407
    +0.15
    0.8%
    1491
    +0.14
    0.7%
    442
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1575
    +0.15
    0.03
    442
    +0.14
    0.03
    1763
    +0.12
    0.02
    Negative Logits
    <bos>
    -1.25
    Ufficio
    -0.54
    Šaltiniai
    -0.52
    /*@
    -0.51
     darted
    -0.50
    Dime
    -0.50
    Selama
    -0.48
    Tira
    -0.48
    orghini
    -0.48
    Fabri
    -0.48
    POSITIVE LOGITS
     Reg
    1.34
     reg
    1.28
    Reg
    1.19
     REG
    1.19
    reg
    1.17
     Regression
    1.07
    Regression
    1.02
    REG
    0.99
     Regis
    0.97
     Regents
    0.96
    Activations Density 0.349%

    No Known Activations