Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 101324
    Prev
    Next
    INDEX
    Explanations

    references to slavery and its historical context

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

    voyage, sailed, African traders

    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
    thoscope
    -0.53
    Underground
    -0.53
    𓃵
    -0.53
    Gambas
    -0.52
     Chwiliwch
    -0.52
    underground
    -0.52
    ExtendWith
    -0.51
     indoors
    -0.50
    الحياه
    -0.49
     مواليد
    -0.48
    POSITIVE LOGITS
    Kaynakça
    0.32
     volando
    0.31
     Cous
    0.30
    ----
    0.29
    发表于
    0.29
     oub
    0.29
     îles
    0.29
    newtheorem
    0.29
     sailed
    0.28
     barcos
    0.28
    Activations Density 0.104%

    No Known Activations