© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 3839
    Prev
    Next
    INDEX
    Explanations

    technical and software-related terms and concepts

    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
    2019
    +0.32
    1.1%
    752
    +0.14
    0.5%
    946
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2019
    +0.32
    0.03
    946
    +0.14
    0.03
    1678
    +0.13
    0.02
    Negative Logits
     actually
    -0.72
     seemed
    -0.65
     to
    -0.65
     specifically
    -0.64
     in
    -0.64
    的
    -0.63
    ologous
    -0.63
     so
    -0.62
     seem
    -0.62
    riften
    -0.62
    POSITIVE LOGITS
     lele
    1.68
     istan
    1.54
     meis
    1.49
     tanga
    1.46
     mef
    1.45
     makro
    1.43
     elek
    1.39
     milano
    1.39
     antik
    1.39
     magis
    1.37
    Activations Density 0.052%

    No Known Activations