© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 1975
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific processes and numerical comparisons in a context of physical phenomena

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

    plasma

    np_acts-logits-general · gemini-2.0-flash

    plasma chemical treatment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     صوتيه
    -0.90
    openzeppelin
    -0.77
    basicConfig
    -0.71
     estimés
    -0.67
    setupUi
    -0.66
    PhysRevD
    -0.66
    graphique
    -0.66
    ScopeManager
    -0.65
     defaultstate
    -0.62
     MotionEvent
    -0.59
    POSITIVE LOGITS
     plasma
    0.78
     plas
    0.62
     Plasma
    0.61
     divert
    0.61
     scrape
    0.59
    Plasma
    0.57
    plasma
    0.55
     limiter
    0.55
     Mercier
    0.54
     polo
    0.54
    Activations Density 0.431%

    No Known Activations