© 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. 2440
    Prev
    Next
    INDEX
    Explanations

    words related to the act of dropping or removing items or concepts

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

    "drop" or "dropping"

    np_acts-logits-general · gemini-2.0-flash

    drop support

    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
     autorytatywna
    -0.71
    setVerticalGroup
    -0.64
     AssemblyTitle
    -0.57
     AssemblyCompany
    -0.57
    enumi
    -0.56
     للمعارف
    -0.56
     Италијани
    -0.54
    دانشنامهٔ
    -0.50
    NameInMap
    -0.50
    RTDA
    -0.49
    POSITIVE LOGITS
     drop
    2.39
    drop
    2.30
     Drop
    2.23
    Drop
    2.17
     dropped
    2.13
     DROP
    2.06
     dropping
    2.05
     drops
    1.94
    dropped
    1.92
    DROP
    1.90
    Activations Density 0.086%

    No Known Activations