© 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. 15405
    Prev
    Next
    INDEX
    Explanations

    references to new or emerging concepts, particularly in technology or species classification

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

    Special characters and symbols

    np_acts-logits-general · gemini-2.0-flash

    new species, parliamentary, chronic, mathematical

    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
    再び
    -0.42
    再次
    -0.41
     Another
    -0.40
    another
    -0.40
    τά
    -0.40
    non
    -0.38
     دیگری
    -0.38
    再度
    -0.37
    added
    -0.37
    itself
    -0.37
    POSITIVE LOGITS
    ########.
    1.11
    KommentareTeilen
    0.93
     ostavi
    0.89
    DoubleQuotes
    0.88
     financières
    0.88
     EconPapers
    0.86
    findpost
    0.86
     AspNetCore
    0.84
    MigrationBuilder
    0.83
    +#+
    0.83
    Activations Density 0.061%

    No Known Activations