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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 7228
    Prev
    Next
    INDEX
    Explanations

    Japanese particles and colloquial expressions used in conversational context

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

    Japanese interjections

    np_acts-logits-general · gemini-2.0-flash

    ああ、つらい、すいません

    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
    турой
    -0.48
    urile
    -0.43
     Searle
    -0.42
    Obras
    -0.42
    beur
    -0.40
     temor
    -0.40
     Mortuary
    -0.40
    a
    -0.39
    sal
    -0.38
    zem
    -0.37
    POSITIVE LOGITS
     CreateTagHelper
    0.90
    ientôt
    0.84
     pinulongan
    0.83
     AssemblyCulture
    0.82
     ddelweddau
    0.81
    InjectAttribute
    0.81
    DockStyle
    0.81
    ImageContext
    0.76
     AspNetCore
    0.75
    GEBURTSDATUM
    0.75
    Activations Density 0.050%

    No Known Activations