© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 112850
    Prev
    Next
    INDEX
    Explanations

    specific terms and phrases related to various contexts including transport, political affiliations, youth, and secrets

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

    "train wreck" / "teenage world" / "marketing campaign"

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    EFIAPI
    -0.49
    TagMode
    -0.46
    دانشنامهٔ
    -0.45
    StoreMessageInfo
    -0.41
    enumi
    -0.40
     '\\;'
    -0.39
    Tikang
    -0.37
    BeginContext
    -0.35
     essendo
    -0.34
    最快更新
    -0.34
    POSITIVE LOGITS
     enfans
    0.55
     Exactos
    0.48
     doInBackground
    0.45
     يتيمه
    0.45
     lenker
    0.45
    ception
    0.43
     pelatih
    0.43
     används
    0.42
     favorites
    0.42
     مؤرشف
    0.42
    Activations Density 0.068%

    No Known Activations