© 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. 20-GEMMASCOPE-RES-16K
    11. 15171
    Prev
    Next
    INDEX
    Explanations

    technical specifications and characteristics related to physical properties and performance metrics

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

    preceding a measureable quantity

    np_acts-logits-general · gemini-2.0-flash

    physical quantities and measurements

    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
     sapere
    -0.54
    γη
    -0.48
     deberes
    -0.45
     órgãos
    -0.44
    haped
    -0.43
     resté
    -0.43
    dolphin
    -0.43
     appunto
    -0.43
     piuttosto
    -0.43
    MENAFN
    -0.42
    POSITIVE LOGITS
     (>
    1.08
    TagMode
    0.89
    IntoConstraints
    0.82
    ValueStyle
    0.79
    (>
    0.78
     वाले
    0.76
    DockStyle
    0.75
     disambiguazione
    0.75
     gynhyrchwyd
    0.74
    expandindo
    0.73
    Activations Density 0.804%

    No Known Activations