© 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. 6494
    Prev
    Next
    INDEX
    Explanations

    expressions related to modern cultural and societal trends

    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
    381
    +0.11
    0.3%
    270
    +0.10
    0.3%
    1445
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    100
    +0.11
    0.03
    270
    +0.10
    0.03
    484
    +0.09
    0.02
    Negative Logits
     meras
    -0.82
     kön
    -0.75
     praktik
    -0.71
     ideolog
    -0.70
     Strukt
    -0.70
     antik
    -0.69
     alkoh
    -0.68
     konserv
    -0.68
     kriminal
    -0.66
     kredit
    -0.65
    POSITIVE LOGITS
     unspeak
    1.28
     horrend
    1.01
     endeavouring
    1.01
     shenan
    1.01
     ineffec
    1.00
     disagre
    0.99
     indestru
    0.99
     vainly
    0.98
     tolerably
    0.96
     gaily
    0.96
    Activations Density 0.269%

    No Known Activations