© 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. 18-GEMMASCOPE-RES-16K
    11. 14094
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial trading and investment opportunities

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

    Imperative verbs like "get," "set," or "battle"

    np_acts-logits-general · gemini-2.0-flash

    discover get enjoy learn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.63
     NSCoder
    -0.61
    ślę
    -0.61
    ::_('
    -0.58
    Hauptartikel
    -0.57
     tartalomajánló
    -0.57
    EDEFAULT
    -0.57
    sprechend
    -0.56
     समीक्षक
    -0.56
     ExecuteAsync
    -0.55
    POSITIVE LOGITS
     discover
    1.07
     get
    1.05
     Enjoy
    1.05
     enjoy
    1.04
     Get
    1.01
    Enjoy
    0.99
     learn
    0.97
    Get
    0.95
    Discover
    0.87
     let
    0.86
    Activations Density 0.163%

    No Known Activations