© 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. 3668
    Prev
    Next
    INDEX
    Explanations

    temporal references and sequencing in events

    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
    +0.23
    0.8%
    453
    +0.14
    0.5%
    1013
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    776
    +0.23
    0.05
    706
    +0.14
    0.04
    1272
    +0.12
    0.04
    Negative Logits
    <bos>
    -1.73
     kwiet
    -0.73
     cushi
    -0.68
     Assorted
    -0.67
     automne
    -0.65
     sierp
    -0.64
     hairc
    -0.64
     endeavoured
    -0.62
     shuddered
    -0.60
     endeavored
    -0.59
    POSITIVE LOGITS
     alkoh
    1.16
     konserv
    1.12
     akade
    1.09
     akut
    1.08
     monaster
    1.06
     kosme
    1.06
     kompati
    1.05
     keramik
    1.04
     minimalis
    1.02
     optik
    1.02
    Activations Density 0.197%

    No Known Activations