© 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. 403
    Prev
    Next
    INDEX
    Explanations

    verbs that suggest uncertainty or conditions surrounding outcomes

    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
    +0.33
    1.4%
    1967
    +0.13
    0.5%
    453
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    862
    +0.33
    0.07
    1937
    +0.13
    0.06
    1023
    +0.11
    0.06
    Negative Logits
    <bos>
    -2.10
     that
    -0.68
    ,
    -0.65
     it
    -0.62
     this
    -0.62
     which
    -0.61
     where
    -0.61
     with
    -0.61
     don
    -0.60
     for
    -0.60
    POSITIVE LOGITS
     pecuni
    1.37
     Minang
    1.36
     stockholm
    1.35
     Muhamma
    1.34
     dises
    1.34
     lele
    1.33
     errone
    1.28
     Jambi
    1.27
     saar
    1.26
     kado
    1.26
    Activations Density 0.584%

    No Known Activations