© 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-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 13393
    Prev
    Next
    INDEX
    Explanations

    references to NBA teams or basketball players

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1777
    +0.14
    0.5%
    1141
    +0.14
    0.5%
    1472
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1141
    +0.14
    0.04
    1351
    +0.14
    0.03
    1178
    +0.13
    0.03
    Negative Logits
     vorrei
    -0.85
     [''
    -0.75
     trovo
    -0.73
     sappi
    -0.72
     claudia
    -0.70
     espri
    -0.69
     surpl
    -0.69
     réfugi
    -0.69
     scopri
    -0.68
     brille
    -0.65
    POSITIVE LOGITS
     basketball
    1.27
     Basketball
    1.17
     NBA
    1.16
    Basketball
    1.12
    NBA
    1.09
    basketball
    0.99
     basket
    0.87
     Basket
    0.81
    basket
    0.76
    Basket
    0.75
    Activations Density 0.152%

    No Known Activations