© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 10230
    Prev
    Next
    INDEX
    Explanations

    phrases related to spatial orientation and positioning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    関数
    -0.30
     professional
    -0.29
    professional
    -0.29
     fog
    -0.29
    struttura
    -0.29
     gang
    -0.28
    ugna
    -0.28
    手下
    -0.27
    profesor
    -0.27
     humanidade
    -0.27
    POSITIVE LOGITS
    IntoConstraints
    1.23
    makeConstraints
    1.11
     position
    0.96
     위치
    0.96
     Position
    0.94
    webElementXpaths
    0.93
    awtextra
    0.92
    AutoresizingMask
    0.91
     placement
    0.88
    setVerticalGroup
    0.84
    Activations Density 0.500%

    No Known Activations