© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 5602
    Prev
    Next
    INDEX
    Explanations

    comparative phrases that indicate superiority or differences in degrees among multiple elements

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

    degree or extent

    np_acts-logits-general · gemini-2.0-flash

    far, higher, beyond, long comparator

    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
    kháu
    -0.52
    addCriterion
    -0.47
    MigrationBuilder
    -0.47
    FunctionFlags
    -0.47
    contentLoaded
    -0.45
    IntoConstraints
    -0.43
    ThemeOverlay
    -0.43
    NewLabel
    -0.42
     GenerationType
    -0.42
     NUKAT
    -0.42
    POSITIVE LOGITS
     far
    0.69
     jauh
    0.58
     langt
    0.57
     daleko
    0.56
    far
    0.55
    раздо
    0.55
     далеко
    0.53
     vastly
    0.50
    远远
    0.47
    훨
    0.45
    Activations Density 0.339%

    No Known Activations