© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3482
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "kind."

    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
    674
    +0.12
    0.3%
    1589
    +0.10
    0.3%
    1438
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1044
    +0.12
    0.04
    1836
    +0.10
    0.02
    390
    +0.08
    0.04
    Negative Logits
     Valenzuela
    -0.50
     Gonz
    -0.48
     управління
    -0.48
    Allister
    -0.48
     Marín
    -0.48
     Schrö
    -0.47
     McLaugh
    -0.47
    Grath
    -0.47
     Azevedo
    -0.46
    Dermott
    -0.46
    POSITIVE LOGITS
    /**
    0.67
     sortes
    0.66
     haer
    0.64
    kinds
    0.63
     dabar
    0.62
    ⓧ
    0.62
     kinds
    0.62
     sort
    0.60
    ;;)
    0.60
    
    0.60
    Activations Density 0.096%

    No Known Activations