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. 16-GEMMASCOPE-RES-16K
    6. 12603
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and health sectors, particularly focusing on death penalty, human health, and public policy implications

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

    preceding capitalized words

    np_acts-logits-general · gemini-2.0-flash

    locations and entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pleaſure
    -0.80
     reaſon
    -0.79
     greateſt
    -0.74
    IntoConstraints
    -0.74
    rungsseite
    -0.74
    BufferException
    -0.73
    TestingModule
    -0.71
     purpoſe
    -0.71
     Houſe
    -0.71
    AndEndTag
    -0.70
    POSITIVE LOGITS
    Portail
    0.64
     environment
    0.61
    entire
    0.50
     world
    0.49
     landscape
    0.47
    THE
    0.47
    Liên
    0.45
     للتو
    0.45
    geme
    0.44
     path
    0.44
    Activations Density 0.915%

    No Known Activations