© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8437
    Prev
    Next
    INDEX
    Explanations

    phrases referring to recent time frames or occurrences

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

    Time periods after "recent" or "coming"

    np_acts-logits-general · gemini-2.0-flash

    recent weeks, months, years

    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
     muualla
    -0.53
    Население
    -0.47
    дарь
    -0.46
     Casserole
    -0.42
    Distribuzione
    -0.41
     trọn
    -0.40
     facie
    -0.39
    pot
    -0.39
    ThemeOverlay
    -0.38
    TagHelpers
    -0.38
    POSITIVE LOGITS
     weeks
    1.61
     years
    1.50
     months
    1.49
     days
    1.37
    weeks
    1.18
    months
    1.13
    years
    1.10
     Months
    1.10
     WEEKS
    1.08
    Weeks
    1.03
    Activations Density 0.101%

    No Known Activations