© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 2378
    Prev
    Next
    INDEX
    Explanations

    phrases related to military actions and airstrikes

    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
    50
    +0.26
    1.0%
    1499
    +0.11
    0.4%
    690
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1499
    +0.26
    0.04
    946
    +0.11
    0.03
    254
    +0.10
    0.03
    Negative Logits
    <bos>
    -3.21
    ⓧ
    -0.75
    /***
    -0.66
    <!--
    -0.60
     adapt
    -0.60
    /**
    -0.59
    #![
    -0.58
    lateinit
    -0.56
    ViewFeatures
    -0.56
    beforeAll
    -0.55
    POSITIVE LOGITS
     unlaw
    1.39
     tucson
    1.35
     jaya
    1.35
     toledo
    1.34
     unwarran
    1.32
     frankfurt
    1.31
     sovere
    1.27
     beverly
    1.26
     Minang
    1.25
     bandung
    1.24
    Activations Density 0.256%

    No Known Activations