© 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. 4348
    Prev
    Next
    INDEX
    Explanations

    citations and references in the document

    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
    +0.28
    1.2%
    1343
    +0.10
    0.4%
    1150
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.28
    0.04
    1148
    +0.10
    0.03
    1973
    +0.07
    0.03
    Negative Logits
    <bos>
    -2.15
    ⓧ
    -1.28
    <?
    -1.06
    /**
    -1.05
    
    -1.00
    /*
    -0.93
    <?
    -0.86
    /***
    -0.72
     springfox
    -0.71
    Transcripción
    -0.71
    POSITIVE LOGITS
    dison
    0.76
     Minang
    0.72
    spectos
    0.65
    yanto
    0.63
     Kemen
    0.62
     cæ
    0.62
     udang
    0.62
     Hitam
    0.62
     maroc
    0.61
     concess
    0.61
    Activations Density 0.079%

    No Known Activations