© 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. 6308
    Prev
    Next
    INDEX
    Explanations

    sentences containing comparisons or contrasts

    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
    381
    +0.14
    0.4%
    382
    +0.13
    0.4%
    2019
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.14
    0.07
    1445
    +0.13
    0.07
    752
    +0.11
    0.04
    Negative Logits
     mcdonald
    -0.61
     ryzen
    -0.60
     bushing
    -0.53
     xdrive
    -0.52
    carolina
    -0.52
     małe
    -0.51
     chrysler
    -0.50
     orlando
    -0.50
     lmfao
    -0.50
     worin
    -0.50
    POSITIVE LOGITS
     Docteur
    1.15
     Mémoires
    1.09
     Chapitre
    1.05
     Sén
    1.05
     Souha
    1.03
     Membre
    1.02
     Traité
    1.00
     coté
    1.00
     Jérusalem
    0.99
     Venise
    0.99
    Activations Density 0.524%

    No Known Activations