© 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. 6141
    Prev
    Next
    INDEX
    Explanations

    phrases related to pets and their well-being

    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
    394
    +0.09
    0.3%
    1842
    +0.09
    0.3%
    906
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.09
    0.06
    177
    +0.09
    0.04
    422
    +0.08
    0.03
    Negative Logits
     RSSSF
    -0.82
     logar
    -0.76
     Wikisource
    -0.75
     revisor
    -0.71
     asfal
    -0.71
     Arxiv
    -0.71
     Annales
    -0.70
     duran
    -0.70
     vides
    -0.68
     Departement
    -0.68
    POSITIVE LOGITS
     shenan
    0.68
     indestru
    0.58
     adorable
    0.56
     Affection
    0.55
     cute
    0.54
     Adorable
    0.51
     bred
    0.51
     cutest
    0.50
    Leider
    0.50
     sentient
    0.49
    Activations Density 0.409%

    No Known Activations