© 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. 2118
    Prev
    Next
    INDEX
    Explanations

    the letter "o" in various forms

    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
    +0.18
    1.1%
    1961
    +0.15
    0.9%
    521
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.18
    0.02
    538
    +0.15
    0.02
    1961
    +0.14
    0.01
    Negative Logits
    <bos>
    -2.01
    Skocz
    -0.63
    Horário
    -0.61
     Queste
    -0.59
     participated
    -0.56
     participate
    -0.56
    AddField
    -0.56
    Kích
    -0.55
     Infatti
    -0.55
    Бан
    -0.53
    POSITIVE LOGITS
     véhic
    1.23
     embodi
    1.21
     impra
    1.19
     unlaw
    1.16
     singuli
    1.14
     unce
    1.11
     malheure
    1.11
     déliv
    1.11
     soulign
    1.10
     élégante
    1.10
    Activations Density 0.081%

    No Known Activations