© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 8035
    Prev
    Next
    INDEX
    Explanations

    phrases indicating existence or state of being

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

    Different forms of "is" in various languages

    np_acts-logits-general · gemini-2.0-flash

    languages indicating "is" or "are"

    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
    moiselle
    -0.53
    Tun
    -0.51
    basedir
    -0.50
    rungsseite
    -0.50
    iconque
    -0.49
    popd
    -0.47
    WaitGroup
    -0.47
    ScopeManager
    -0.47
     Zah
    -0.47
     Tun
    -0.46
    POSITIVE LOGITS
     là
    0.94
     adalah
    0.93
     είναι
    0.85
    是
    0.84
     merupakan
    0.77
     são
    0.76
     является
    0.75
    ίναι
    0.75
    เป็น
    0.74
     Somos
    0.74
    Activations Density 0.175%

    No Known Activations