© 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. 5247
    Prev
    Next
    INDEX
    Explanations

    information related to contamination and health risks associated with a specific chemical compound

    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
    198
    +0.17
    0.5%
    674
    +0.11
    0.3%
    964
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.17
    0.06
    1424
    +0.11
    0.04
    184
    +0.10
    0.01
    Negative Logits
     Filosof
    -0.59
     Visite
    -0.52
     Voiture
    -0.51
     Meksi
    -0.51
     Quelques
    -0.51
     Sitten
    -0.51
     Voyez
    -0.50
     Mémoires
    -0.50
     Però
    -0.50
     Mémoire
    -0.50
    POSITIVE LOGITS
     suscep
    0.98
     suscepti
    0.88
     swarovski
    0.84
     vulnerable
    0.78
     unprotected
    0.76
     susceptible
    0.75
     scrat
    0.73
     unknowingly
    0.73
     friable
    0.72
     squa
    0.72
    Activations Density 0.582%

    No Known Activations