© 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. 13183
    Prev
    Next
    INDEX
    Explanations

    locations in Asia, specifically mentioning India or China

    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
    1842
    +0.16
    0.5%
    394
    +0.11
    0.4%
    1009
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.16
    0.10
    1842
    +0.11
    0.05
    198
    +0.11
    0.05
    Negative Logits
    <bos>
    -0.95
     gynnwys
    -0.69
     Paglinawan
    -0.68
     '\\;'
    -0.66
    YMS
    -0.65
     وتسجيلات
    -0.64
    enderror
    -0.63
    TagMode
    -0.62
    abetes
    -0.62
     actionMode
    -0.61
    POSITIVE LOGITS
     unspeak
    2.12
     unwarran
    2.04
     McLaugh
    1.99
     reluct
    1.97
     disagre
    1.97
     apprehen
    1.94
     affor
    1.93
     increa
    1.92
     depic
    1.90
     inev
    1.85
    Activations Density 1.085%

    No Known Activations