© 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. 7393
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to geographical locations, particularly in India

    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
    1034
    +0.15
    0.6%
    506
    +0.15
    0.5%
    1515
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.15
    0.03
    438
    +0.15
    0.03
    755
    +0.13
    0.03
    Negative Logits
     Punj
    -0.71
     Banjar
    -0.68
     karna
    -0.62
     jaya
    -0.60
     muna
    -0.58
     Karang
    -0.56
     KPK
    -0.56
     Minang
    -0.55
     Muhamma
    -0.55
     bahay
    -0.55
    POSITIVE LOGITS
     Beng
    1.02
     Bangladesh
    0.98
     Bengali
    0.96
     Bengal
    0.96
    Beng
    0.95
    Bangladesh
    0.90
     Banglades
    0.87
     Bengals
    0.86
     beng
    0.79
     Mejía
    0.68
    Activations Density 0.141%

    No Known Activations