© 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. 7143
    Prev
    Next
    INDEX
    Explanations

    terms related to geopolitics and technology

    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
    1870
    +0.15
    0.5%
    1978
    +0.12
    0.4%
    678
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1870
    +0.15
    0.03
    678
    +0.12
    0.05
    1510
    +0.11
    0.04
    Negative Logits
    FormTagHelper
    -0.65
     initComponents
    -0.58
     Halen
    -0.56
     Poehler
    -0.55
    RRect
    -0.54
    DataPropertyName
    -0.54
    postDelayed
    -0.52
     AssemblyCulture
    -0.51
    htbp
    -0.49
    invokeLater
    -0.49
    POSITIVE LOGITS
     effe
    1.10
     nece
    1.08
    Huhu
    1.03
     Aprile
    1.02
     Augu
    1.02
     fta
    1.01
     ivi
    1.01
     aen
    1.01
    Noice
    0.99
    Lmfao
    0.97
    Activations Density 0.337%

    No Known Activations