© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 13376
    Prev
    Next
    INDEX
    Explanations

    phrases indicating default settings or configurations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    "default" and related word forms

    np_acts-logits-general · gemini-2.0-flash

    default value

    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
    Negative Logits
    queryInterface
    -0.63
    expandindo
    -0.62
    ExtendWith
    -0.59
     jsPsych
    -0.57
    ValueStyle
    -0.55
    الإنجليزية
    -0.54
    SequentialGroup
    -0.52
    enumi
    -0.50
    IsMutable
    -0.50
    Tembelea
    -0.50
    POSITIVE LOGITS
     default
    1.15
     Default
    1.02
    default
    1.01
    Default
    0.98
    默认
    0.95
     defaults
    0.94
    デフォ
    0.93
    setDefault
    0.86
     默认
    0.85
     getDefault
    0.85
    Activations Density 0.290%

    No Known Activations