© 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. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 10181
    Prev
    Next
    INDEX
    Explanations

    terms related to the connections and components of mechanical devices, particularly focusing on ends and connectors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Italijanski
    -0.48
    RegressionTest
    -0.45
     المعيارى
    -0.44
     betweenstory
    -0.43
     Савезне
    -0.42
    цездатний
    -0.40
    vician
    -0.40
     macetas
    -0.38
     bershka
    -0.38
     LAP
    -0.38
    POSITIVE LOGITS
     ujung
    0.80
    extrémité
    0.75
     ends
    0.70
     extremity
    0.69
     terminal
    0.68
     terminus
    0.68
    terminal
    0.65
     end
    0.65
     Spitze
    0.61
     ponta
    0.61
    Activations Density 0.893%

    No Known Activations