© 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
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 10450
    Prev
    Next
    INDEX
    Explanations

    attributes and advantages of systems or methods, emphasizing efficiency and reliability

    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
     يتيمه
    -0.67
    rungsseite
    -0.54
     chied
    -0.50
    Daftar
    -0.50
    Ngày
    -0.47
    ⓧ
    -0.46
     Wicidata
    -0.45
     chiesto
    -0.45
    BeginContext
    -0.45
     StringTokenizer
    -0.45
    POSITIVE LOGITS
     excellent
    0.49
     efficiency
    0.43
    ')")
    0.42
     attractive
    0.41
     efficient
    0.41
     highly
    0.40
    AnchorStyles
    0.40
     adaptability
    0.40
     simplicity
    0.39
     advantages
    0.39
    Activations Density 0.173%

    No Known Activations