© 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. 12786
    Prev
    Next
    INDEX
    Explanations

    attributes related to technical issues or problems

    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
    1839
    +0.09
    0.3%
    868
    +0.08
    0.2%
    581
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1839
    +0.09
    0.04
    197
    +0.08
    0.04
    75
    +0.08
    0.03
    Negative Logits
     indestru
    -1.33
     reluct
    -1.24
     gaily
    -1.17
     suscep
    -1.15
     impra
    -1.14
     apprehen
    -1.14
     unspeak
    -1.13
     unve
    -1.13
     disagre
    -1.13
     maneu
    -1.10
    POSITIVE LOGITS
    quality
    0.77
     quality
    0.76
    bootstrapcdn
    0.76
     Paglinawan
    0.74
     Seeder
    0.70
     morales
    0.69
     sexu
    0.66
     psychiat
    0.66
     Himo
    0.66
    LEncoder
    0.65
    Activations Density 0.271%

    No Known Activations