© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4311
    Prev
    Next
    INDEX
    Explanations

    references to online purchasing and delivery services

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

    Precedes a product, service, or profession

    np_acts-logits-general · gemini-2.0-flash

    online purchasing and services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    expandindo
    -0.75
     nahilalakip
    -0.75
     estekak
    -0.71
     nakalista
    -0.69
    Geplaatst
    -0.66
    Хьажоргаш
    -0.62
     CURIAM
    -0.60
     utafitiHapana
    -0.59
     CanadaChoose
    -0.57
     Boswell
    -0.56
    POSITIVE LOGITS
    ivent
    0.31
     объя
    0.28
     العن
    0.28
     купить
    0.28
    Купить
    0.27
    binant
    0.27
    oure
    0.27
    üyada
    0.26
     stabili
    0.26
     ELECTRON
    0.26
    Activations Density 0.137%

    No Known Activations