© 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. 13295
    Prev
    Next
    INDEX
    Explanations

    phrases related to comparing and contrasting different elements

    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
    1387
    +0.13
    0.4%
    1325
    +0.12
    0.4%
    1981
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1981
    +0.13
    0.03
    223
    +0.12
    0.03
    1387
    +0.12
    0.03
    Negative Logits
    FlatAppearance
    -0.53
    lcccccc
    -0.49
     Leith
    -0.47
     Estrella
    -0.47
    Ké
    -0.46
     Wul
    -0.46
     Sosa
    -0.45
     Wyn
    -0.45
     Vann
    -0.44
     dikt
    -0.43
    POSITIVE LOGITS
     comparisons
    1.08
     comparing
    1.08
     comparison
    1.08
     compare
    1.08
     compares
    1.05
     comparaison
    0.98
     Comparison
    0.97
    Compare
    0.96
     Compare
    0.96
     Comparisons
    0.95
    Activations Density 0.078%

    No Known Activations