© 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-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 16146
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software development and specific software features

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    674
    +0.47
    1.9%
    251
    +0.16
    0.6%
    732
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.47
    0.04
    732
    +0.16
    0.03
    395
    +0.11
    0.04
    Negative Logits
     lele
    -1.31
     ananas
    -1.25
     bont
    -1.23
     moza
    -1.17
     hina
    -1.15
     kaos
    -1.14
     kac
    -1.13
     kado
    -1.12
     alpes
    -1.12
     kade
    -1.10
    POSITIVE LOGITS
    ⓧ
    1.26
    <bos>
    1.25
    
    1.10
    /**
    1.10
    <?
    1.04
    <?
    0.93
    FTFY
    0.82
    /*
    0.81
    /***
    0.79
    Lmfao
    0.77
    Activations Density 0.369%

    No Known Activations