© 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 - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 50317
    Prev
    Next
    INDEX
    Explanations

    the term "EMT" and references to associated concepts, suggesting a focus on cellular processes and transitions, particularly in the context of cancer

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

    loo, Voodoo, EMT

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    ValueStyle
    -0.73
     Савезне
    -0.69
    뀜
    -0.67
     AssemblyCompany
    -0.66
     initComponents
    -0.63
    ﴿
    -0.63
    WriteTagHelper
    -0.62
    исленность
    -0.60
    TypedDataSet
    -0.60
     المعيارى
    -0.60
    POSITIVE LOGITS
     loo
    0.78
     Loo
    0.68
     př
    0.68
    Loo
    0.61
    Doo
    0.57
     Doo
    0.55
     kangaroo
    0.54
    할
    0.53
    BeforeAll
    0.50
    viewWillAppear
    0.49
    Activations Density 0.006%

    No Known Activations