© 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. 15306
    Prev
    Next
    INDEX
    Explanations

    elements related to agricultural practices and their effects

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

    preceding a period

    np_acts-logits-general · gemini-2.0-flash

    frequency, size, types

    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
     והוא
    -1.32
    이고
    -1.13
    并且
    -1.03
    ConstraintMaker
    -1.01
    并将
    -0.94
     and
    -0.91
     but
    -0.90
     ويمكن
    -0.89
    并
    -0.86
     ولم
    -0.84
    POSITIVE LOGITS
     accordingly
    0.82
     thereafter
    0.79
     therefrom
    0.70
     respectively
    0.66
     Италијани
    0.61
     withal
    0.61
    stle
    0.61
    respectively
    0.59
     thereon
    0.59
     दोनों
    0.59
    Activations Density 1.544%

    No Known Activations