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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 8632
    Prev
    Next
    INDEX
    Explanations

    phrases related to online platform features and user benefits

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

    Follows a period

    np_acts-logits-general · gemini-2.0-flash

    Massachusetts State Police

    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
     المعيارى
    -0.63
    contentInset
    -0.55
     iirc
    -0.54
    anair
    -0.53
     IIRC
    -0.53
    ("${
    -0.51
    一応
    -0.50
    chine
    -0.50
    ::_('
    -0.49
    mycin
    -0.49
    POSITIVE LOGITS
     enjoy
    1.28
     Enjoy
    1.25
    Enjoy
    1.23
     discover
    1.08
    enjoy
    1.01
     get
    0.97
     explore
    0.95
     learn
    0.94
     Get
    0.89
    Discover
    0.89
    Activations Density 0.152%

    No Known Activations