© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 591
    Prev
    Next
    INDEX
    Explanations

    Present-tense constructions combined with references to time and current events

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

    "now"

    np_acts-logits-general · gemini-2.0-flash

    present time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     initially
    -0.44
    Initialize
    -0.40
     inicialmente
    -0.40
     tenuto
    -0.40
     earlier
    -0.39
     wcześniej
    -0.39
     Sociedade
    -0.39
    setFirstName
    -0.38
     दौरान
    -0.38
     Vries
    -0.37
    POSITIVE LOGITS
     now
    0.86
     Now
    0.85
    Now
    0.79
    now
    0.79
     ahora
    0.71
     NOW
    0.70
     Теперь
    0.68
    NOW
    0.68
     теперь
    0.67
    Теперь
    0.67
    Activations Density 0.286%

    No Known Activations