© 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. 6394
    Prev
    Next
    INDEX
    Explanations

    information related to court cases and legal doctrines

    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
    +0.18
    0.5%
    1741
    +0.10
    0.3%
    1648
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.18
    0.02
    499
    +0.10
    0.02
    1499
    +0.09
    0.02
    Negative Logits
     unlaw
    -1.11
     swarovski
    -1.06
     cushi
    -1.05
     impractica
    -1.03
     unwarran
    -1.03
     tupperware
    -1.03
     hairc
    -1.01
     nutella
    -1.01
     unspeak
    -1.00
     shenan
    -0.97
    POSITIVE LOGITS
     kug
    0.93
     makro
    0.90
     kasa
    0.89
     duk
    0.83
     kac
    0.82
     alkoh
    0.80
     akut
    0.79
     Antik
    0.79
     fisk
    0.77
     kule
    0.77
    Activations Density 0.077%

    No Known Activations