© 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. 4602
    Prev
    Next
    INDEX
    Explanations

    references to platforms and their functionalities

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

    "platform" or "platforms"

    np_acts-logits-general · gemini-2.0-flash

    platform to support or develop

    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
     JsonConvert
    -0.51
     незавершена
    -0.51
    )++;
    -0.48
     "'");
    -0.46
    javadoc
    -0.45
    CheckedChanged
    -0.45
     Pep
    -0.45
     Reſ
    -0.43
    :^{
    -0.43
    avadoc
    -0.42
    POSITIVE LOGITS
     platform
    2.42
    platform
    2.17
     Platform
    2.13
    Platform
    2.11
     PLATFORM
    2.09
     platforms
    2.08
     plataforma
    1.97
     Plattform
    1.94
     Platforms
    1.94
    PLATFORM
    1.93
    Activations Density 0.060%

    No Known Activations