© 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. 40-GEMMASCOPE-RES-16K
    11. 4321
    Prev
    Next
    INDEX
    Explanations

    references to numerical data or statistics related to health

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    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
    -0.52
    ceğine
    -0.51
    SequentialGroup
    -0.48
    ulaski
    -0.43
     naive
    -0.43
    resizingMask
    -0.42
     للمعارف
    -0.42
    reportWebVitals
    -0.40
    Hall
    -0.40
    Trajectory
    -0.39
    POSITIVE LOGITS
    +:+
    0.51
    ⤹
    0.45
     صوتيه
    0.45
    Xna
    0.38
    LayoutStyle
    0.37
     يتيمه
    0.36
    ̈́
    0.35
    LLocation
    0.33
    ècie
    0.33
    brica
    0.33
    Activations Density 0.703%

    No Known Activations