© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 3138
    Prev
    Next
    INDEX
    Explanations

    key concepts and terminology related to cavity quantum electrodynamics (QED) systems

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

    Cavity quantum electrodynamics (QED) systems

    np_acts-logits-general · gemini-2.0-flash

    cavity-QED systems

    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
    matchCondition
    -0.46
    icali
    -0.40
    ╞
    -0.40
    glTexCoord
    -0.39
    oa̍t
    -0.37
     BoxFit
    -0.36
     всего
    -0.36
    dcmtk
    -0.36
    fromLTRB
    -0.36
    SerializedName
    -0.36
    POSITIVE LOGITS
    URLException
    0.43
     Sénat
    0.42
    Gravity
    0.41
    Manipulation
    0.40
    GEBURTSDATUM
    0.39
    WebServlet
    0.39
    منابع
    0.38
    basicConfig
    0.37
     Вікі
    0.37
    gravity
    0.36
    Activations Density 1.543%

    No Known Activations