© 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 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. 11638
    Prev
    Next
    INDEX
    Explanations

    descriptive details about clothing and fashion

    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
    1385
    +0.25
    0.8%
    1343
    +0.14
    0.5%
    736
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.25
    0.07
    1385
    +0.14
    0.05
    678
    +0.11
    0.04
    Negative Logits
     errone
    -0.99
     incess
    -0.95
     hairc
    -0.94
     pecuni
    -0.93
     democra
    -0.92
     bayern
    -0.90
     praktik
    -0.90
     ekos
    -0.89
     kram
    -0.87
     alkoh
    -0.86
    POSITIVE LOGITS
     espagnole
    0.61
     souci
    0.59
     heureuse
    0.58
     italienne
    0.55
     religieuse
    0.54
     allemande
    0.54
     decorative
    0.53
     classNames
    0.52
     allé
    0.52
     fidèle
    0.52
    Activations Density 0.356%

    No Known Activations