© 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. 785
    Prev
    Next
    INDEX
    Explanations

    information related to cultural practices and laws in a specific location

    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
    1842
    +0.17
    0.5%
    509
    +0.13
    0.4%
    394
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1380
    +0.17
    0.03
    509
    +0.13
    0.07
    81
    +0.12
    0.03
    Negative Logits
     marcato
    -0.75
     gila
    -0.71
     teri
    -0.71
     cabrio
    -0.69
     azzurro
    -0.67
     giù
    -0.67
     geforce
    -0.66
     logitech
    -0.65
     gioca
    -0.64
     Teks
    -0.63
    POSITIVE LOGITS
     União
    0.45
     strict
    0.45
    Să
    0.43
    Acest
    0.43
     worin
    0.41
    enums
    0.41
     fundamental
    0.41
    Și
    0.41
    Fordítás
    0.40
    Források
    0.40
    Activations Density 0.556%

    No Known Activations