© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 12116
    Prev
    Next
    INDEX
    Explanations

    phrases related to the Pacific region and specific locations within it

    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
    303
    +0.12
    0.5%
    1506
    +0.11
    0.4%
    201
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    303
    +0.12
    0.02
    201
    +0.11
    0.01
    1194
    +0.11
    0.01
    Negative Logits
    setDo
    -0.53
    prehensive
    -0.50
     Verm
    -0.49
     CreateTagHelper
    -0.48
    jstor
    -0.47
     cubana
    -0.45
     rollo
    -0.45
     Oneida
    -0.45
    !");
    
    -0.44
     Laredo
    -0.44
    POSITIVE LOGITS
     Pacific
    1.39
    Pacific
    1.31
     Pac
    1.22
     pacific
    1.15
     PACIFIC
    1.09
    Pac
    1.06
    pacific
    1.01
     PAC
    0.95
    PAC
    0.93
     pac
    0.91
    Activations Density 0.056%

    No Known Activations