© 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. 3-GEMMASCOPE-RES-16K
    11. 3753
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notation related to functions and variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     premier
    -0.62
     PREMIER
    -0.62
     ब्रेकडाउन
    -0.60
    premier
    -0.59
    Premier
    -0.59
    errHandler
    -0.58
    richTextPanel
    -0.58
     Premier
    -0.57
     premiere
    -0.54
     PREMI
    -0.52
    POSITIVE LOGITS
    prime
    0.73
    Fantastic
    0.57
     prime
    0.54
    fantastic
    0.53
     Fantastic
    0.52
     fantastic
    0.52
    apple
    0.50
    <tbody>
    0.48
    interopRequire
    0.45
     createState
    0.43
    Activations Density 0.046%

    No Known Activations