© 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. 11778
    Prev
    Next
    INDEX
    Explanations

    numerical values embedded within text

    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
    1343
    +0.12
    0.4%
    1870
    +0.11
    0.3%
    609
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    609
    +0.12
    0.07
    1527
    +0.11
    0.05
    382
    +0.10
    0.05
    Negative Logits
    Ανα
    -0.62
    Consejo
    -0.62
    municipi
    -0.59
     himo
    -0.59
    Palmar
    -0.57
    Πε
    -0.56
    IonicModule
    -0.56
    ViewFeatures
    -0.56
    DoubleQuotes
    -0.56
    Från
    -0.56
    POSITIVE LOGITS
     disreg
    1.10
     suscep
    1.09
     increa
    0.99
     scrat
    0.96
     impra
    0.95
     maneu
    0.92
     milf
    0.91
     aen
    0.90
     invin
    0.88
     hairc
    0.88
    Activations Density 0.209%

    No Known Activations