© 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. 3707
    Prev
    Next
    INDEX
    Explanations

    expressions of humorous or sarcastic commentary

    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%
    906
    +0.17
    0.7%
    736
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    906
    +0.26
    -0.01
    1419
    +0.17
    0.05
    381
    +0.11
    0.03
    Negative Logits
    <bos>
    -2.00
     meras
    -0.97
     nyeri
    -0.92
     ló
    -0.90
     Walkover
    -0.88
     trám
    -0.87
     kilomet
    -0.86
     rú
    -0.84
    ItemBackground
    -0.83
    Sqft
    -0.83
    POSITIVE LOGITS
     impra
    2.25
     reluct
    2.24
     affor
    2.23
     accla
    2.19
     disagre
    2.11
     maneu
    2.11
     increa
    2.05
     indestru
    2.01
     shenan
    1.99
     impractica
    1.99
    Activations Density 1.043%

    No Known Activations