© 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. 7010
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and internet use

    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
    198
    +0.19
    0.5%
    227
    +0.14
    0.4%
    605
    +0.12
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.19
    0.07
    16
    +0.14
    0.07
    752
    +0.12
    0.04
    Negative Logits
     Paglinawan
    -0.73
    Đây
    -0.71
    <bos>
    -0.70
    titleMargin
    -0.66
    Trước
    -0.65
     يتيمه
    -0.65
    Ông
    -0.63
    Còn
    -0.63
    styleType
    -0.63
     chuyền
    -0.62
    POSITIVE LOGITS
     Juf
    2.00
     reluct
    1.84
     secon
    1.78
     impra
    1.77
     increa
    1.77
     inext
    1.76
     intermitt
    1.76
     Confu
    1.73
     squa
    1.73
     unden
    1.72
    Activations Density 0.533%

    No Known Activations