© 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. 790
    Prev
    Next
    INDEX
    Explanations

    phrases related to political controversies and legal actions

    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
    1482
    +0.19
    0.7%
    1296
    +0.17
    0.7%
    61
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1296
    +0.19
    0.07
    1482
    +0.17
    0.06
    61
    +0.14
    0.04
    Negative Logits
    mschrijving
    -0.49
     slika
    -0.47
    Zunanje
    -0.47
     uhr
    -0.46
     thuy
    -0.45
    emples
    -0.45
    oteur
    -0.44
     izdel
    -0.43
     quoc
    -0.43
    cciale
    -0.43
    POSITIVE LOGITS
    life
    1.22
     life
    1.21
     Life
    1.15
    Life
    1.15
    LIFE
    1.14
     LIFE
    1.14
     LIF
    0.92
     lifes
    0.88
     lif
    0.88
    lifes
    0.86
    Activations Density 0.098%

    No Known Activations