© 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. 11147
    Prev
    Next
    INDEX
    Explanations

    names of individuals

    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
    1741
    +0.17
    0.5%
    453
    +0.16
    0.5%
    50
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    981
    +0.17
    0.04
    1141
    +0.16
    0.03
    1373
    +0.11
    0.01
    Negative Logits
     maneu
    -1.50
     scrat
    -1.49
     increa
    -1.49
     impra
    -1.48
     shenan
    -1.45
     reluct
    -1.44
     hairc
    -1.42
     practition
    -1.38
     disreg
    -1.38
     cushi
    -1.37
    POSITIVE LOGITS
     StatefulWidget
    0.82
    FlatAppearance
    0.81
    FlatStyle
    0.80
    Literat
    0.72
     StatelessWidget
    0.70
     nonatomic
    0.69
    ExtendWith
    0.69
    Ekster
    0.68
    DriverManager
    0.67
    Notae
    0.67
    Activations Density 0.057%

    No Known Activations