© 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. 6974
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal or legislative matters

    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
    +0.41
    3.1%
    1870
    +0.05
    0.4%
    1741
    +0.05
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1403
    +0.41
    0.24
    15
    +0.05
    0.25
    800
    +0.05
    0.26
    Negative Logits
     despotism
    -1.35
     belliger
    -1.34
     ruinous
    -1.25
     unspeak
    -1.19
     massacres
    -1.14
     unlaw
    -1.14
     ineffectual
    -1.13
     disgra
    -1.12
     odious
    -1.12
     nukes
    -1.11
    POSITIVE LOGITS
    <bos>
    13.42
    GEBURTSDATUM
    2.38
    expandindo
    2.32
    Autoritní
    2.22
     betweenstory
    2.19
    تقاوى
    2.00
     Italijani
    1.94
     '\\;'
    1.87
     Administrativna
    1.85
     Paglinawan
    1.81
    Activations Density 0.084%

    No Known Activations