© 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. 10994
    Prev
    Next
    INDEX
    Explanations

    references to technology products, specifically related to downloading software and tutorials

    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
    227
    +0.19
    0.6%
    1150
    +0.16
    0.5%
    1699
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.19
    0.08
    981
    +0.16
    0.07
    924
    +0.12
    0.06
    Negative Logits
    Wię
    -1.02
    Abraços
    -0.97
    Díky
    -0.96
    Obrigada
    -0.95
    Dlaczego
    -0.94
     Porém
    -0.92
    Menurutnya
    -0.91
    Și
    -0.91
    Abraço
    -0.91
    Доброго
    -0.91
    POSITIVE LOGITS
     fta
    1.05
     fash
    1.03
     lola
    1.02
     effe
    1.01
     contex
    0.99
     tew
    0.98
     noel
    0.97
     casio
    0.96
     fto
    0.96
     laun
    0.96
    Activations Density 0.405%

    No Known Activations