© 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 EvalsExportsAPI 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. 11541
    Prev
    Next
    INDEX
    Explanations

    technical terms related to technology and programming

    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
    184
    +0.15
    0.5%
    1343
    +0.10
    0.3%
    1741
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    648
    +0.15
    0.03
    74
    +0.10
    0.03
    227
    +0.09
    0.05
    Negative Logits
     reluct
    -0.98
     ingrat
    -0.90
     beaute
    -0.88
     milf
    -0.88
     indestru
    -0.87
     madonna
    -0.87
     cuck
    -0.86
     disagre
    -0.84
     gaily
    -0.84
     parch
    -0.84
    POSITIVE LOGITS
     quoque
    0.69
     eorum
    0.63
     ones
    0.62
     habet
    0.61
    Transcrip
    0.61
    Preliminaries
    0.60
     magis
    0.57
    *}[
    0.56
    Histology
    0.55
    Tecnologia
    0.55
    Activations Density 0.327%

    No Known Activations