© 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. 249
    Prev
    Next
    INDEX
    Explanations

    titles of movies or books, particularly those that include "The."

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

    "The" at the beginning of sentences or titles

    np_acts-logits-general · gemini-2.0-flash

    titles of books, movies, or claims

    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
    Personensuche
    -0.70
     disambiguazione
    -0.69
     justement
    -0.62
     wikipagina
    -0.58
     invece
    -0.56
    ########.
    -0.56
     entière
    -0.56
     zelve
    -0.56
     dites
    -0.55
     Catalana
    -0.54
    POSITIVE LOGITS
     forgotten
    0.69
     return
    0.67
     Return
    0.63
     tale
    0.62
     golden
    0.62
     battle
    0.61
    ories
    0.61
     rise
    0.60
     lost
    0.60
    irs
    0.59
    Activations Density 0.205%

    No Known Activations