© 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. 326
    Prev
    Next
    INDEX
    Explanations

    references to the U.S. government or federal entities

    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
    +0.22
    0.9%
    1425
    +0.10
    0.4%
    683
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1479
    +0.22
    0.07
    1425
    +0.10
    0.06
    30
    +0.09
    0.05
    Negative Logits
    <bos>
    -2.90
    ⓧ
    -0.89
    /**
    -0.68
     winked
    -0.66
     give
    -0.66
     ensure
    -0.65
     rehabilitate
    -0.65
     deepen
    -0.65
     stabilize
    -0.64
    hyrchwyd
    -0.64
    POSITIVE LOGITS
     silikon
    1.68
     keramik
    1.59
     lele
    1.53
     Meksi
    1.52
     Præ
    1.52
     alkoh
    1.51
     magis
    1.48
     Græ
    1.46
     nomine
    1.46
     mikrofon
    1.45
    Activations Density 0.124%

    No Known Activations