© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 5210
    Prev
    Next
    INDEX
    Explanations

    information related to sports teams, games, and events

    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
    +0.20
    0.8%
    1828
    +0.09
    0.4%
    1837
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    304
    +0.20
    -0.00
    1213
    +0.09
    0.07
    113
    +0.09
    0.04
    Negative Logits
     MÁ
    -0.74
     ù
    -0.71
     dali
    -0.69
     abr
    -0.67
     adal
    -0.64
     stras
    -0.63
     abstra
    -0.63
     pels
    -0.62
     Himo
    -0.61
     solidar
    -0.60
    POSITIVE LOGITS
     McInt
    1.09
     Yugos
    1.01
     McLaugh
    0.89
     ecru
    0.89
     mortgagee
    0.86
     cuban
    0.86
     seclu
    0.84
     Middles
    0.82
     philanth
    0.81
     manila
    0.81
    Activations Density 0.372%

    No Known Activations