© 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. 6255
    Prev
    Next
    INDEX
    Explanations

    information related to business operations, financial transactions, and news reports

    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
    674
    +0.15
    0.5%
    1047
    +0.10
    0.3%
    814
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1047
    +0.15
    0.03
    814
    +0.10
    0.02
    1416
    +0.10
    0.03
    Negative Logits
    COMPR
    -0.55
    SpringBootTest
    -0.54
    Ekster
    -0.52
    shadowOpacity
    -0.52
    晰
    -0.49
    CrossOrigin
    -0.49
     ElevatedButton
    -0.47
    Causas
    -0.47
    Veel
    -0.47
    Vrij
    -0.46
    POSITIVE LOGITS
     Messieurs
    1.20
     territo
    1.03
     honn
    1.01
     Mémoires
    1.01
     dises
    0.95
     rafra
    0.95
     saar
    0.95
     ordina
    0.94
     erad
    0.92
     déchir
    0.91
    Activations Density 0.076%

    No Known Activations