© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 10360
    Prev
    Next
    INDEX
    Explanations

    specific military terminology and references to the Korean War

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

    Korean War and oil circuits/systems

    np_acts-logits-general · gemini-2.0-flash

    Korean War, oil pressure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.70
    ioutil
    -0.63
    styleType
    -0.59
     propOrder
    -0.58
    invokeLater
    -0.58
     rhestr
    -0.57
     CanadaChoose
    -0.57
    findpost
    -0.56
    SharedCtor
    -0.55
     snippetHide
    -0.55
    POSITIVE LOGITS
     Oil
    0.33
     Conſ
    0.33
    basicConfig
    0.32
    Oil
    0.31
     proszę
    0.30
    difference
    0.29
     масло
    0.29
     Reſ
    0.29
    corner
    0.28
     conflits
    0.28
    Activations Density 0.255%

    No Known Activations