© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 12533
    Prev
    Next
    INDEX
    Explanations

    terms related to physical movements and medical procedures in the context of scientific research

    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
    736
    +0.08
    0.2%
    604
    +0.08
    0.2%
    455
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    455
    +0.08
    0.03
    707
    +0.08
    0.04
    1409
    +0.07
    0.02
    Negative Logits
     kram
    -1.02
     persil
    -0.98
     antik
    -0.96
     lele
    -0.94
     Kategor
    -0.92
     valla
    -0.91
     alkoh
    -0.91
     meras
    -0.90
     ananas
    -0.89
     makro
    -0.89
    POSITIVE LOGITS
     would
    0.92
     could
    0.90
     will
    0.85
     might
    0.83
     may
    0.81
     can
    0.80
     wouldn
    0.76
    Może
    0.75
     creates
    0.74
     constitutes
    0.69
    Activations Density 0.314%

    No Known Activations