© 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. 5433
    Prev
    Next
    INDEX
    Explanations

    references to legal cases and amendments

    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
    872
    +0.16
    0.5%
    1499
    +0.13
    0.4%
    499
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1499
    +0.16
    0.05
    499
    +0.13
    0.04
    417
    +0.08
    0.03
    Negative Logits
     nutella
    -0.85
     thermomix
    -0.74
     tupperware
    -0.73
     swarovski
    -0.72
     tricot
    -0.63
     Ename
    -0.60
     ecru
    -0.60
     bonbons
    -0.58
     oreo
    -0.57
     lycra
    -0.54
    POSITIVE LOGITS
     Karang
    0.67
     Nguy
    0.62
     Pekan
    0.59
     Badan
    0.56
     nā
    0.56
     Agung
    0.56
     Ukraina
    0.55
    landmark
    0.54
     Mexique
    0.54
     Cik
    0.53
    Activations Density 0.226%

    No Known Activations