© 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. 5268
    Prev
    Next
    INDEX
    Explanations

    questions and phrases related to analysis, evaluation, and inquiry

    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
    1108
    +0.13
    0.4%
    872
    +0.08
    0.2%
    569
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1108
    +0.13
    0.05
    1893
    +0.08
    0.03
    240
    +0.08
    0.02
    Negative Logits
     lele
    -0.82
     maksi
    -0.72
     kasa
    -0.70
     Meksi
    -0.70
     roh
    -0.67
     kaos
    -0.66
     saar
    -0.64
     Istri
    -0.63
     Okt
    -0.63
     lemp
    -0.63
    POSITIVE LOGITS
     begs
    0.68
     question
    0.67
     questions
    0.61
    Dichloroethene
    0.57
     womit
    0.52
     Questions
    0.51
     wondering
    0.51
    question
    0.50
     Question
    0.49
     wonder
    0.49
    Activations Density 0.342%

    No Known Activations