© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 10662
    Prev
    Next
    INDEX
    Explanations

    similes and comparative phrases

    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
    +0.10
    0.3%
    906
    +0.07
    0.2%
    1343
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    3
    +0.10
    0.04
    1885
    +0.07
    0.03
    106
    +0.07
    0.03
    Negative Logits
     indescri
    -0.62
     unspeak
    -0.52
     cushi
    -0.49
     cuban
    -0.46
    FloatField
    -0.45
     quivering
    -0.44
     bonnie
    -0.44
     luxuriant
    -0.43
     tiffany
    -0.43
     cruelly
    -0.43
    POSITIVE LOGITS
     déput
    0.78
     Gouvernement
    0.77
     viciss
    0.75
     sappi
    0.74
     Sén
    0.74
     Siamo
    0.71
     Docteur
    0.70
     affez
    0.67
     Sì
    0.66
     territo
    0.66
    Activations Density 0.187%

    No Known Activations