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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 4195
    Prev
    Next
    INDEX
    Explanations

    terms indicating a broad variety or extent in application or range

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

    "Wide" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    wide scope

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IBOutlet
    -0.77
    PRNewswire
    -0.68
    ReusableCell
    -0.66
    argout
    -0.60
    tfrac
    -0.60
     <<<<<<<<<<<<<<
    -0.60
    MigrationBuilder
    -0.60
     Baller
    -0.58
     trajets
    -0.58
    Scénario
    -0.58
    POSITIVE LOGITS
     scope
    1.02
     wide
    1.00
     broad
    0.98
     Wide
    0.96
    Wide
    0.95
    WIDE
    0.95
     breadth
    0.94
     widening
    0.93
     widest
    0.93
     WIDE
    0.92
    Activations Density 0.176%

    No Known Activations