© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 4248
    Prev
    Next
    INDEX
    Explanations

    transitional phrases and logical connectors in arguments

    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
    +0.35
    1.7%
    752
    +0.11
    0.5%
    1499
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1265
    +0.35
    0.08
    2019
    +0.11
    0.10
    100
    +0.11
    0.06
    Negative Logits
    <bos>
    -3.09
    /***
    -0.70
     repatri
    -0.65
     mobilize
    -0.61
     turned
    -0.61
     reunite
    -0.61
     marched
    -0.61
     cooperated
    -0.61
     plead
    -0.60
     started
    -0.60
    POSITIVE LOGITS
     bandung
    1.72
     jaya
    1.63
     aen
    1.37
     jawa
    1.37
     lele
    1.35
     Minang
    1.34
     jati
    1.34
     haup
    1.29
     saha
    1.27
     surabaya
    1.27
    Activations Density 1.113%

    No Known Activations