Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 8008
    Prev
    Next
    INDEX
    Explanations

    references to mobile devices and their features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "phone" or "phones"

    np_acts-logits-general · gemini-2.0-flash

    phoneArena.com

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WaitGroup
    -0.39
     boletos
    -0.39
    multer
    -0.37
    AddTagHelper
    -0.36
     samarbeid
    -0.34
    sobí
    -0.34
    addGap
    -0.33
     Keuangan
    -0.32
     réserv
    -0.32
     instalaciones
    -0.32
    POSITIVE LOGITS
     phones
    1.09
     smartphone
    1.06
     Phones
    1.02
     smartphones
    1.02
     Smartphone
    0.98
     handset
    0.96
     Android
    0.96
     phone
    0.95
     Nokia
    0.94
    smartphone
    0.92
    Activations Density 0.440%

    No Known Activations