© 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. 5530
    Prev
    Next
    INDEX
    Explanations

    programming-related tokens and function names

    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
    50
    +0.20
    0.7%
    876
    +0.19
    0.6%
    1577
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    876
    +0.20
    -0.01
    523
    +0.19
    0.05
    1871
    +0.16
    0.07
    Negative Logits
    TagMode
    -0.65
     протяжении
    -0.61
     cả
    -0.60
    微软
    -0.60
     그는
    -0.60
    Demografia
    -0.59
    اریخ
    -0.59
    ズ
    -0.59
    México
    -0.58
     Архивировано
    -0.58
    POSITIVE LOGITS
     effe
    2.07
     !...
    2.00
     ?...
    1.97
     impra
    1.96
     increa
    1.93
     suscep
    1.92
     unden
    1.91
     intermitt
    1.90
     inev
    1.89
     desir
    1.87
    Activations Density 1.473%

    No Known Activations