© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 117
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to the concept of "Po" or its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     otomatig
    -0.71
    ChildScrollView
    -0.70
    -------
    -0.69
    reportWebVitals
    -0.65
     Administrativna
    -0.61
    tagHelperRunner
    -0.61
     виправивши
    -0.59
    transQ
    -0.57
    Sqft
    -0.57
    Irv
    -0.56
    POSITIVE LOGITS
     Po
    0.48
    Po
    0.37
    لاثة
    0.31
     Poy
    0.29
    ExecuteReader
    0.29
     зрения
    0.28
     По
    0.28
     Poz
    0.27
    ulating
    0.27
     délic
    0.26
    Activations Density 0.695%

    No Known Activations