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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 5478
    Prev
    Next
    INDEX
    Explanations

    instructions related to food preparation and storage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Items stored/placed in a refrigerator/freezer

    np_acts-logits-general · gemini-2.0-flash

    refrigerator or freezer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wol
    -0.56
     Berufs
    -0.51
    quiao
    -0.50
    @[+][
    -0.50
     cenu
    -0.50
    flame
    -0.48
    Extrait
    -0.47
     fleas
    -0.47
     Traction
    -0.45
    KTM
    -0.45
    POSITIVE LOGITS
     refrigerated
    1.22
     refrigerator
    1.21
     refrigerate
    1.21
     fridge
    1.15
     refrigeration
    1.13
     freezer
    1.07
    refriger
    1.01
     Refrigerator
    0.99
     Refrigeration
    0.97
    Refriger
    0.97
    Activations Density 0.153%

    No Known Activations