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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 19-GEMMASCOPE-RES-16K
    6. 11298
    Prev
    Next
    INDEX
    Explanations

    references to protein and fluid dynamics mechanisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idosis
    -0.51
    eclampsia
    -0.46
    StoryboardSegue
    -0.45
    getSystemService
    -0.45
     Scopus
    -0.44
     makeStyles
    -0.43
    Butyl
    -0.43
    отно
    -0.42
     notar
    -0.42
     bombings
    -0.42
    POSITIVE LOGITS
    تقاوى
    0.84
     molecules
    0.83
     particles
    0.74
     kaarangay
    0.73
     components
    0.72
    IMPORTED
    0.71
     constituents
    0.71
     particules
    0.64
    DockStyle
    0.63
    dersfield
    0.63
    Activations Density 1.453%

    No Known Activations