© 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. 9-GEMMASCOPE-RES-16K
    6. 5855
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to political organizations and events in Swaziland

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

    after "Dla" or "zini"

    np_acts-logits-general · gemini-2.0-flash

    Manzini Police Station

    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
    offsetof
    -0.38
     documenting
    -0.37
     documentation
    -0.34
     Paulista
    -0.34
    Litteratur
    -0.34
    makeText
    -0.34
    EndTag
    -0.33
    mergeFrom
    -0.33
     PIT
    -0.33
     $('<
    -0.32
    POSITIVE LOGITS
    aziland
    0.77
     defaultstate
    0.61
     desertcart
    0.60
    Personensuche
    0.58
    出版年
    0.57
     Brunei
    0.56
    setVerticalGroup
    0.56
     ujednoznacz
    0.55
     disambiguazione
    0.54
    évaluateur
    0.53
    Activations Density 0.352%

    No Known Activations