© 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. 5761
    Prev
    Next
    INDEX
    Explanations

    references to comic books or series

    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
    1870
    +0.14
    0.5%
    405
    +0.11
    0.4%
    1557
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    994
    +0.14
    0.03
    1836
    +0.11
    0.02
    486
    +0.11
    0.02
    Negative Logits
     >=",
    -0.70
     <>",
    -0.69
     CreateTagHelper
    -0.68
     wattpad
    -0.66
    SBATCH
    -0.65
     كومونز
    -0.65
    RectangleBorder
    -0.62
     الحره
    -0.61
    Зноскі
    -0.61
    onViewCreated
    -0.60
    POSITIVE LOGITS
     comic
    1.35
     comics
    1.31
    Comic
    1.15
     Comic
    1.14
    comic
    1.12
     Comics
    1.01
    Comics
    0.96
    comics
    0.95
    漫画
    0.58
     comedy
    0.58
    Activations Density 0.075%

    No Known Activations