© 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. 20-GEMMASCOPE-RES-16K
    11. 8789
    Prev
    Next
    INDEX
    Explanations

    academic citations and references within the text

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

    Acronyms or abbreviations after parentheses

    np_acts-logits-general · gemini-2.0-flash

    abbreviations ending in A

    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
     Belén
    -0.64
    SharedCtor
    -0.64
     referenties
    -0.61
     Orrell
    -0.60
    NameInMap
    -0.58
    EndProject
    -0.55
     виправивши
    -0.55
    UnknownFieldSet
    -0.55
     EIF
    -0.54
     Yiddish
    -0.54
    POSITIVE LOGITS
    MSA
    0.78
    TSA
    0.76
    SPA
    0.73
    EA
    0.72
    NDA
    0.72
    TCA
    0.71
    VA
    0.71
    XA
    0.70
    CTA
    0.70
    DCA
    0.70
    Activations Density 0.339%

    No Known Activations