© 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. 1893
    Prev
    Next
    INDEX
    Explanations

    expressions related to quantities and measurements

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

    Actions related to filling or measuring liquid

    np_acts-logits-general · gemini-2.0-flash

    liquid measurement and filling

    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
     الحره
    -0.50
    afficheront
    -0.46
    celona
    -0.43
    GTCX
    -0.41
     modelAndView
    -0.41
    lesias
    -0.39
     COMPANY
    -0.39
    ablecer
    -0.39
     Zentral
    -0.38
     bVar
    -0.38
    POSITIVE LOGITS
     fill
    0.55
    Fill
    0.52
    fill
    0.52
    messageInfo
    0.50
     Fill
    0.50
    FILL
    0.50
     EconPapers
    0.50
     Filling
    0.47
     FILL
    0.47
     mengisi
    0.47
    Activations Density 0.397%

    No Known Activations