© 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. 6167
    Prev
    Next
    INDEX
    Explanations

    nutritional information and health-related terms

    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
    896
    +0.12
    0.4%
    1961
    +0.11
    0.3%
    1265
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.12
    0.09
    1052
    +0.11
    0.06
    1174
    +0.10
    0.04
    Negative Logits
     alkoh
    -0.89
     canne
    -0.89
     marte
    -0.86
     kosme
    -0.85
     Lombar
    -0.84
     meis
    -0.83
     franz
    -0.82
     siff
    -0.82
     kac
    -0.82
     elek
    -0.81
    POSITIVE LOGITS
     Pliocene
    0.76
     sclero
    0.66
     cilia
    0.65
     Eocene
    0.64
     oocytes
    0.64
     Miocene
    0.63
     userType
    0.62
     friable
    0.62
     zirc
    0.61
     uplands
    0.61
    Activations Density 0.742%

    No Known Activations