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

    Neuronpedia

    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. 1917
    Prev
    Next
    INDEX
    Explanations

    descriptive events related to law enforcement operations

    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
    946
    +0.15
    0.5%
    690
    +0.12
    0.4%
    2019
    +0.12
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    946
    +0.15
    0.06
    382
    +0.12
    0.05
    539
    +0.12
    0.04
    Negative Logits
     ordina
    -1.14
     espé
    -1.02
     cannes
    -1.01
     fré
    -1.01
     maniere
    -1.01
     gouver
    -0.99
     renou
    -0.99
     trouva
    -0.98
     obé
    -0.97
     pét
    -0.97
    POSITIVE LOGITS
    vyšší
    0.65
     розта
    0.63
     someone
    0.62
     they
    0.61
     suddenly
    0.61
     another
    0.61
     somebody
    0.60
    Další
    0.60
     when
    0.59
     зді
    0.59
    Activations Density 0.265%

    No Known Activations