© 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. 6165
    Prev
    Next
    INDEX
    Explanations

    phrases related to programming and implementation details

    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
    1842
    +0.18
    0.5%
    1150
    +0.14
    0.4%
    1967
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1322
    +0.18
    0.05
    441
    +0.14
    0.05
    752
    +0.13
    0.04
    Negative Logits
    você
    -0.55
    bitField
    -0.54
     ویکی‌پدی
    -0.52
    Asimismo
    -0.51
     informou
    -0.51
    Fonto
    -0.50
     respondeu
    -0.49
    Conclusão
    -0.49
    Ekster
    -0.49
     Apesar
    -0.48
    POSITIVE LOGITS
     them
    0.93
     siena
    0.76
     chèvre
    0.75
    them
    0.74
     ananas
    0.72
     memberId
    0.68
     THEM
    0.68
     Mère
    0.67
     tarte
    0.67
     claudia
    0.64
    Activations Density 0.761%

    No Known Activations