© 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. 3842
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific name or term related to "Pra" and its variations

    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
    intios
    -0.42
    рович
    -0.37
    テンツ
    -0.35
    ember
    -0.34
    şen
    -0.32
     Kiz
    -0.32
    RouterModule
    -0.32
    vation
    -0.32
    webElementGuid
    -0.31
    luit
    -0.31
    POSITIVE LOGITS
     Pra
    2.73
    Pra
    2.66
     pra
    2.45
    pra
    2.36
     PRA
    1.93
    PRA
    1.55
     Пра
    1.54
     Practical
    1.45
    Пра
    1.45
    Practical
    1.43
    Activations Density 1.267%

    No Known Activations