© 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. 793
    Prev
    Next
    INDEX
    Explanations

    items related to food and cooking, particularly descriptions of ingredients, dishes, and preparation methods

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

    a surface or covering

    np_acts-logits-general · gemini-2.0-flash

    covered or coated surfaces

    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
    escalier
    -0.58
    setVerticalGroup
    -0.57
    DllImport
    -0.52
     koncentr
    -0.52
    satisfied
    -0.51
    qrstuvwxyz
    -0.50
    ensaft
    -0.50
     المعيارى
    -0.50
     conservazione
    -0.49
    accepted
    -0.49
    POSITIVE LOGITS
     covered
    1.53
     coated
    1.31
     adorned
    1.27
     decorated
    1.25
     Covered
    1.20
    Covered
    1.17
    covered
    1.06
     topped
    1.05
     decked
    1.05
     equipped
    1.04
    Activations Density 0.514%

    No Known Activations