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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 9248
    Prev
    Next
    INDEX
    Explanations

    topics related to sustainability and waste management

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

    recycling

    np_acts-logits-general · gemini-2.0-flash

    recycling and sustainability actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الحره
    -0.65
    Personendaten
    -0.60
    quelize
    -0.57
    withstanding
    -0.56
     PublicKey
    -0.54
     CURIAM
    -0.54
    spelling
    -0.53
     FetchType
    -0.53
    ̍
    -0.53
    Filmografie
    -0.53
    POSITIVE LOGITS
     recycling
    1.47
     recycled
    1.43
     reuse
    1.30
     recycle
    1.28
     Recycling
    1.25
     recy
    1.24
     reused
    1.23
     recyclable
    1.19
    Recy
    1.18
    Recycling
    1.17
    Activations Density 0.147%

    No Known Activations