© 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. 12721
    Prev
    Next
    INDEX
    Explanations

    details about the arrangement of molecules in ice crystals

    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
    876
    +0.17
    0.6%
    906
    +0.17
    0.5%
    872
    +0.17
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.17
    0.07
    872
    +0.17
    0.07
    876
    +0.17
    -0.02
    Negative Logits
     kompati
    -0.93
     Gouver
    -0.78
     kriminal
    -0.78
     kosme
    -0.78
     akut
    -0.77
     Juventud
    -0.75
     kontinu
    -0.75
     republi
    -0.73
     Asunción
    -0.72
     konkre
    -0.71
    POSITIVE LOGITS
     embodi
    0.67
     pollut
    0.66
     geometries
    0.63
     flocc
    0.63
     shapes
    0.63
     shape
    0.61
     ennemi
    0.61
     poft
    0.59
     TEMPLATE
    0.58
     geometry
    0.58
    Activations Density 0.786%

    No Known Activations