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. 4955
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate customer engagement and interaction

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

    Followed by a modal verb or preposition

    np_acts-logits-general · gemini-2.0-flash

    you can

    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
     obtain
    -0.69
     obtaining
    -0.62
     vardır
    -0.62
     Thus
    -0.58
     değildir
    -0.57
     thus
    -0.56
     utiliza
    -0.55
     persons
    -0.53
     obtains
    -0.53
     cannot
    -0.52
    POSITIVE LOGITS
    StoryboardSegue
    0.84
     مشين
    0.80
     Савезне
    0.77
     تضيفلها
    0.75
    Datuak
    0.74
     grandkids
    0.74
     تانيه
    0.73
     MainAxisSize
    0.72
    IsContent
    0.72
     محفوظة
    0.72
    Activations Density 0.022%

    No Known Activations