© 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. 775
    Prev
    Next
    INDEX
    Explanations

    details related to people, their activities, and personal information

    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
    +0.09
    0.2%
    906
    +0.07
    0.2%
    1597
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1597
    +0.09
    0.03
    1461
    +0.07
    0.04
    450
    +0.07
    0.03
    Negative Logits
    SPECIFIED
    -0.58
    IUrlHelper
    -0.54
     behar
    -0.50
     reik
    -0.50
     soeur
    -0.49
     laim
    -0.49
    stdbool
    -0.49
     aisladas
    -0.48
    ợt
    -0.47
    ONESIA
    -0.47
    POSITIVE LOGITS
     depic
    0.79
     imgur
    0.74
     renfer
    0.74
     squa
    0.72
     emphat
    0.69
     gettyimages
    0.68
     hugo
    0.66
     romeo
    0.66
     hentai
    0.66
     unsplash
    0.65
    Activations Density 0.272%

    No Known Activations