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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4831
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific measurements and calculations in physics

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

    Mathematical/scientific terminology

    np_acts-logits-general · gemini-2.0-flash

    physical and mathematical concepts

    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
    tagHelperRunner
    -0.73
     صوتيه
    -0.68
     hebdomada
    -0.64
    Personensuche
    -0.63
     transfieras
    -0.60
     GenerationType
    -0.60
    تقاوى
    -0.59
    ########.
    -0.57
    🏻‍♀️
    -0.55
    iosamente
    -0.54
    POSITIVE LOGITS
     probed
    0.69
     near
    0.67
     around
    0.61
     inside
    0.59
     away
    0.58
     induced
    0.56
     governed
    0.56
     parametri
    0.56
     corresponding
    0.54
     nahe
    0.52
    Activations Density 2.177%

    No Known Activations