© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 5267
    Prev
    Next
    INDEX
    Explanations

    URL links and technical terms related to web connections and errors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StoryboardSegue
    -0.95
     ویکی‌پدی
    -0.92
     EconPapers
    -0.88
    TagMode
    -0.87
     queſta
    -0.87
     surla
    -0.85
     שוליים
    -0.84
    MigrationBuilder
    -0.81
    Rohy
    -0.81
    Дереккөздер
    -0.80
    POSITIVE LOGITS
    1
    0.35
    ↵
    0.34
     constitucional
    0.30
    <eos>
    0.30
    2
    0.28
     extranjero
    0.27
     Constitución
    0.27
     Democrá
    0.25
     faites
    0.25
     volontaire
    0.25
    Activations Density 3.717%

    No Known Activations