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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 6654
    Prev
    Next
    INDEX
    Explanations

    references to mobile devices and their associated technologies

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

    Cell phones and mobile devices

    np_acts-logits-general · gemini-2.0-flash

    mobile phones and smartphones

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sunter
    -0.68
    skosten
    -0.63
    UVWXYZ
    -0.57
    LayoutPanel
    -0.55
    ----</
    -0.54
     dirait
    -0.54
     дописавши
    -0.53
    peinture
    -0.53
    yntaxException
    -0.53
    ouncil
    -0.52
    POSITIVE LOGITS
     smartphone
    2.18
     phones
    2.16
     smartphones
    2.11
     Smartphone
    1.98
     phone
    1.97
     Smartphones
    1.88
     mobile
    1.85
     iPhone
    1.84
     cellphone
    1.84
     Phones
    1.79
    Activations Density 0.371%

    No Known Activations