© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 1719
    Prev
    Next
    INDEX
    Explanations

    references to tea and coffee beverages.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @dribnet

    references to tea and its related health benefits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Einfluß
    -0.41
     nakalista
    -0.41
     Absch
    -0.39
     ύ
    -0.39
     istimewa
    -0.38
     present
    -0.38
     nabíz
    -0.38
     mengh
    -0.38
     được
    -0.37
     Orts
    -0.37
    POSITIVE LOGITS
    Tea
    0.93
     tea
    0.93
     Tea
    0.86
     yoga
    0.69
    tea
    0.66
    India
    0.65
     India
    0.63
    awtextra
    0.63
    Yoga
    0.57
    TEA
    0.57
    Activations Density 0.130%

    No Known Activations