© 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. 3731
    Prev
    Next
    INDEX
    Explanations

    punctuation marks at the end of sentences

    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
    1.4%
    382
    +0.23
    1.2%
    1535
    +0.22
    1.1%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.28
    0.15
    1535
    +0.23
    0.11
    2034
    +0.22
    0.13
    Negative Logits
    <bos>
    -2.38
    ⓧ
    -1.27
    /**
    -1.13
    
    -1.07
    <?
    -1.03
    /*
    -0.98
    /***
    -0.92
    ///**
    -0.86
    Transcripción
    -0.81
    #
    -0.80
    POSITIVE LOGITS
     lele
    1.30
     maroc
    1.15
     roul
    1.14
     accla
    1.11
     kac
    1.08
     jaya
    1.07
     déchir
    1.06
     maneu
    1.06
     épu
    1.03
    emmel
    1.03
    Activations Density 0.543%

    No Known Activations