© 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. 13313
    Prev
    Next
    INDEX
    Explanations

    concepts related to political and economic issues

    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
    674
    +0.38
    1.5%
    184
    +0.16
    0.6%
    1137
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.38
    0.05
    1137
    +0.16
    0.05
    204
    +0.11
    0.03
    Negative Logits
     kosme
    -0.83
     Historie
    -0.76
     protokol
    -0.74
     klinik
    -0.73
     etik
    -0.72
     mikrofon
    -0.72
     grafik
    -0.70
     ikon
    -0.69
     koordin
    -0.69
     Kombin
    -0.69
    POSITIVE LOGITS
     unspeak
    1.46
     apprehen
    1.22
     intersper
    1.21
     shenan
    1.19
     indescri
    1.19
     indestru
    1.18
     inconce
    1.17
     impelled
    1.16
     ardour
    1.10
     pamph
    1.09
    Activations Density 0.287%

    No Known Activations