© 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. 4644
    Prev
    Next
    INDEX
    Explanations

    terms related to the relationships between representations, gestures, and language in the context of motor actions

    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
    674
    +0.10
    0.3%
    872
    +0.07
    0.2%
    814
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1241
    +0.10
    0.03
    1615
    +0.07
    0.04
    226
    +0.07
    0.02
    Negative Logits
     specialmente
    -0.48
    LookAnd
    -0.47
     albic
    -0.46
     piemē
    -0.45
     variabel
    -0.44
    chymal
    -0.43
     magari
    -0.43
     ļ
    -0.43
     kupa
    -0.42
     farbe
    -0.40
    POSITIVE LOGITS
     inseparable
    0.76
     intertwined
    0.72
     coexist
    0.71
     inextrica
    0.70
     interchangeably
    0.69
     together
    0.68
     interdependent
    0.66
     interrelated
    0.66
     simultaneously
    0.66
     synerg
    0.65
    Activations Density 0.401%

    No Known Activations