© 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. 16-GEMMASCOPE-RES-16K
    11. 8701
    Prev
    Next
    INDEX
    Explanations

    details about businesses and their operations, particularly in finance and hospitality

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

    Locations or events

    np_acts-logits-general · gemini-2.0-flash

    venues and activities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ılık
    -0.49
     bague
    -0.47
    jela
    -0.46
    تقاوى
    -0.45
    romycin
    -0.45
    主義
    -0.45
     учё
    -0.45
     esquerda
    -0.45
    olahan
    -0.44
    主义
    -0.44
    POSITIVE LOGITS
     corporate
    0.70
     aboard
    0.65
     hotel
    0.64
     airport
    0.59
     Aéroport
    0.59
     getSystem
    0.59
     school
    0.59
     captive
    0.59
     Corporate
    0.59
    jsdelivr
    0.59
    Activations Density 0.314%

    No Known Activations