© 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-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 5946
    Prev
    Next
    INDEX
    Explanations

    phrases related to political and social issues, including references to governmental systems, elections, protests, and social challenges

    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
    1045
    +0.07
    0.2%
    1650
    +0.07
    0.2%
    761
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1415
    +0.07
    0.03
    1334
    +0.07
    0.04
    299
    +0.06
    0.04
    Negative Logits
     Mlle
    -0.97
     fortn
    -0.95
     sputnik
    -0.93
     reconno
    -0.93
     accla
    -0.88
     indestru
    -0.88
     malheureux
    -0.88
     gild
    -0.86
     michelin
    -0.86
     Motos
    -0.86
    POSITIVE LOGITS
     handle
    0.76
     withstand
    0.69
     cope
    0.67
    <>
    0.64
    setToolTipText
    0.63
    handle
    0.63
    клопе
    0.61
     оригіналу
    0.60
     properly
    0.58
    Beneficios
    0.57
    Activations Density 0.304%

    No Known Activations