© 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. 5510
    Prev
    Next
    INDEX
    Explanations

    references to violent or dangerous situations

    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
    +0.11
    0.3%
    906
    +0.10
    0.3%
    972
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    972
    +0.11
    0.03
    736
    +0.10
    0.03
    946
    +0.09
    0.03
    Negative Logits
     vort
    -0.72
     hant
    -0.65
    SharedDtor
    -0.64
     vola
    -0.62
     sement
    -0.61
     Milán
    -0.60
     fides
    -0.60
     tenda
    -0.59
     biss
    -0.59
     anse
    -0.57
    POSITIVE LOGITS
     lying
    0.64
    Lying
    0.62
     Lying
    0.62
     simpsons
    0.61
     journées
    0.60
     McLaugh
    0.60
     leçons
    0.57
     négociations
    0.56
     unve
    0.54
     séjours
    0.54
    Activations Density 0.126%

    No Known Activations