© 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. 11801
    Prev
    Next
    INDEX
    Explanations

    locations and events related to immigration and border crossings

    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
    856
    +0.14
    0.4%
    939
    +0.13
    0.4%
    1842
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    939
    +0.14
    0.06
    856
    +0.13
    0.04
    1499
    +0.10
    0.04
    Negative Logits
     disreg
    -0.91
     tupperware
    -0.90
     hoody
    -0.86
    !!</
    -0.83
     disgra
    -0.83
     embodi
    -0.82
     scrat
    -0.81
     :)</
    -0.80
     indestru
    -0.80
     affez
    -0.78
    POSITIVE LOGITS
     border
    0.81
    RectangleBorder
    0.75
     neighbouring
    0.70
     borders
    0.70
     neighboring
    0.66
     adjoining
    0.64
     adjacent
    0.63
     Border
    0.61
     bordering
    0.58
    Border
    0.58
    Activations Density 0.262%

    No Known Activations