© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3877
    Prev
    Next
    INDEX
    Explanations

    references to annual events and traditions

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

    "year" or "annual" events

    np_acts-logits-general · gemini-2.0-flash

    annual or yearly events

    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
    stdc
    -0.45
    Legături
    -0.45
     prossima
    -0.42
     retrô
    -0.40
     đang
    -0.39
     senhora
    -0.39
     titolata
    -0.39
     sessão
    -0.39
     boîtier
    -0.39
     distância
    -0.39
    POSITIVE LOGITS
     yearly
    0.75
     annual
    0.73
    annual
    0.71
     anual
    0.68
     annually
    0.68
    yearly
    0.65
    Annual
    0.64
     annuel
    0.61
     brukar
    0.60
     jähr
    0.60
    Activations Density 0.242%

    No Known Activations