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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 30795
    Prev
    Next
    INDEX
    Explanations

    references to the Ebola virus and its impact

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

    Ebola outbreaks and its impact

    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
     ProtoMessage
    -0.55
     AssemblyCulture
    -0.51
    ConstraintMaker
    -0.44
    surate
    -0.42
    ApiOperation
    -0.42
    ContentLoaded
    -0.40
     EconPapers
    -0.39
     trout
    -0.39
     dil
    -0.39
    ViewFeatures
    -0.38
    POSITIVE LOGITS
     Ebola
    0.94
    stdafx
    0.47
     outbreak
    0.43
     financiación
    0.42
     África
    0.41
     Hidup
    0.41
    таратура
    0.40
     Liberia
    0.40
     emergencia
    0.39
     černá
    0.39
    Activations Density 0.018%

    No Known Activations