© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 9965
    Prev
    Next
    INDEX
    Explanations

    actions related to physical manipulation and control systems

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

    ending in "ing", "ed", or "tion"

    np_acts-logits-general · gemini-2.0-flash

    verbs indicating action or change

    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
    хьтан
    -0.59
    InputBorder
    -0.54
    ViewImports
    -0.53
     חיצוניים
    -0.53
    ContentAsync
    -0.51
    InitVars
    -0.50
    -------------</
    -0.50
    InstanceState
    -0.49
    verifyException
    -0.49
    Répondre
    -0.48
    POSITIVE LOGITS
    Tazama
    0.35
    RemoveField
    0.34
     GRATU
    0.31
     herself
    0.30
     gewel
    0.30
    tikal
    0.30
     matrícula
    0.29
     Kammer
    0.28
     altering
    0.28
     rumput
    0.28
    Activations Density 1.733%

    No Known Activations