© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 352
    Prev
    Next
    INDEX
    Explanations

    references to the term "Prime" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    501
    +0.15
    0.9%
    757
    +0.15
    0.9%
    871
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    501
    +0.15
    0.02
    757
    +0.15
    0.02
    871
    +0.14
    0.02
    Negative Logits
    <bos>
    -1.90
    ⓧ
    -0.64
    /**
    -0.64
    /*!
    -0.60
    <?
    -0.58
     interact
    -0.57
    <?
    -0.57
    /***
    -0.57
     manage
    -0.56
    zydent
    -0.56
    POSITIVE LOGITS
     Pri
    1.45
    Pri
    1.26
    pri
    1.15
     pri
    1.08
     PRIM
    1.04
     PRI
    1.01
     ricardo
    0.94
     Pria
    0.93
     shutterstock
    0.92
     pixabay
    0.91
    Activations Density 0.062%

    No Known Activations