© 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. 11827
    Prev
    Next
    INDEX
    Explanations

    phrases related to crime and law enforcement

    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
    1150
    +0.09
    0.3%
    1042
    +0.08
    0.2%
    1939
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    946
    +0.09
    0.06
    1315
    +0.08
    0.04
    1804
    +0.07
    0.06
    Negative Logits
     stik
    -0.87
     trist
    -0.86
     anse
    -0.81
     utop
    -0.78
     kram
    -0.78
     erk
    -0.77
     rente
    -0.77
     biss
    -0.76
     alkoh
    -0.75
     erd
    -0.75
    POSITIVE LOGITS
     him
    0.74
     Mr
    0.61
     Și
    0.57
    him
    0.56
     împre
    0.54
     hänen
    0.52
     Oltre
    0.52
     resemb
    0.52
     Lmao
    0.52
     acesta
    0.52
    Activations Density 0.987%

    No Known Activations