© 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. 20-GEMMASCOPE-RES-16K
    6. 13769
    Prev
    Next
    INDEX
    Explanations

    instances of statistical significance and relevant numerical data in the context of medical or scientific studies

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

    Text before citations

    np_acts-logits-general · gemini-2.0-flash

    citations followed by names or periods

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    tagHelperRunner
    -0.55
    TagMode
    -0.51
    PreferredItem
    -0.48
    WithIOException
    -0.48
    ChildScrollView
    -0.45
    ScopeManager
    -0.44
    llum
    -0.42
     الحره
    -0.42
    TagHelpers
    -0.42
     muñecas
    -0.41
    POSITIVE LOGITS
     resourceCulture
    0.56
     armé
    0.40
    AutoModerator
    0.40
    Bref
    0.37
    üf
    0.36
     sinal
    0.36
     Anw
    0.36
    甚至
    0.36
    ALARM
    0.36
    ImageContext
    0.36
    Activations Density 0.597%

    No Known Activations