© 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. 15855
    Prev
    Next
    INDEX
    Explanations

    words related to Japanese media culture, particularly names and terminology associated with specific characters and settings

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

    Japanese and related foreign words

    np_acts-logits-general · gemini-2.0-flash

    Japanese greetings and finishers

    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
    HtmlAttribute
    -0.75
    tvguidetime
    -0.58
    isEqualTo
    -0.58
     Jpn
    -0.58
     Syner
    -0.58
     оригіналу
    -0.57
    bindParam
    -0.57
     circula
    -0.56
     Administrativna
    -0.56
    Aktualisiert
    -0.55
    POSITIVE LOGITS
    最快更新
    0.50
    raszam
    0.46
    EndContext
    0.45
     كومونز
    0.44
     no
    0.43
     ň
    0.43
    يكب
    0.43
     skuto
    0.41
     Dernière
    0.41
     snippetHide
    0.39
    Activations Density 0.183%

    No Known Activations