© 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 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. 9655
    Prev
    Next
    INDEX
    Explanations

    technical terms and references related to file types and their extensions

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

    File extensions or file-related terms

    np_acts-logits-general · gemini-2.0-flash

    file extensions and MIME types

    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
    RegressionTest
    -0.38
     MainAxisSize
    -0.38
    wpi
    -0.34
    AutoModerator
    -0.34
    ſelf
    -0.33
    blico
    -0.32
    chartInstance
    -0.32
     tour
    -0.32
     betweenstory
    -0.32
     tibia
    -0.31
    POSITIVE LOGITS
     /\.(
    0.70
    spli
    0.70
    rungsseite
    0.68
    :✨
    0.60
    extensions
    0.60
     tartalomajánló
    0.59
     extensão
    0.57
     /\.
    0.57
    EXTENSION
    0.57
    extension
    0.56
    Activations Density 0.320%

    No Known Activations