© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 1441
    Prev
    Next
    INDEX
    Explanations

    expressions indicating frequency or temporal context

    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%
    2034
    +0.15
    0.6%
    1372
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.28
    0.07
    1372
    +0.15
    0.07
    1013
    +0.10
    0.07
    Negative Logits
    <bos>
    -3.48
    ///**
    -0.86
    /***
    -0.84
    <?
    -0.80
    Fordítás
    -0.80
    ⓧ
    -0.79
    Vegeu
    -0.77
    #![
    -0.71
    Autoritní
    -0.70
    Související
    -0.69
    POSITIVE LOGITS
     lele
    1.46
     seksi
    1.31
     kasa
    1.30
     maroc
    1.30
     maske
    1.29
     kaos
    1.29
     kase
    1.26
     antik
    1.26
     jaya
    1.25
     kafe
    1.25
    Activations Density 0.372%

    No Known Activations