© 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. 5149
    Prev
    Next
    INDEX
    Explanations

    numerical measurements and figures

    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
    900
    +0.09
    0.3%
    597
    +0.09
    0.3%
    609
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    609
    +0.09
    0.06
    870
    +0.09
    0.05
    1036
    +0.09
    0.01
    Negative Logits
     Spisak
    -0.64
     dè
    -0.62
     mús
    -0.61
     sò
    -0.59
     alpes
    -0.57
     Bourgoin
    -0.56
     stoff
    -0.56
     krim
    -0.56
     chi̍t
    -0.54
     saar
    -0.54
    POSITIVE LOGITS
     disreg
    0.67
     purplish
    0.55
     suscep
    0.54
     embodi
    0.53
     flocc
    0.52
     scrat
    0.51
     useAuth
    0.51
     pymysql
    0.49
    satin
    0.49
     Mitochond
    0.49
    Activations Density 0.316%

    No Known Activations