© 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. 4236
    Prev
    Next
    INDEX
    Explanations

    references to locations being used for specific purposes

    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
    +0.32
    1.2%
    939
    +0.18
    0.7%
    1013
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    939
    +0.32
    0.12
    964
    +0.18
    0.06
    1438
    +0.13
    0.05
    Negative Logits
    <bos>
    -2.71
     drap
    -0.74
     tille
    -0.72
     stik
    -0.71
     kras
    -0.68
     vla
    -0.67
     tyn
    -0.64
     lapto
    -0.64
    ⓧ
    -0.63
    <?
    -0.63
    POSITIVE LOGITS
    Sklici
    0.81
     tortas
    0.75
     asado
    0.74
     mascarpone
    0.74
     frito
    0.70
     churrasco
    0.70
     fusca
    0.69
     soulign
    0.68
     barbacoa
    0.68
     polenta
    0.68
    Activations Density 1.116%

    No Known Activations