© 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. 15-GEMMASCOPE-RES-16K
    11. 2028
    Prev
    Next
    INDEX
    Explanations

    references to time and recent events, especially in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Statistiche
    -0.55
     stronie
    -0.53
    AsUp
    -0.49
    offerta
    -0.46
     Nacionales
    -0.46
    yordu
    -0.44
     śmierci
    -0.43
     olej
    -0.43
     üzere
    -0.43
     〈
    -0.43
    POSITIVE LOGITS
    TagMode
    0.84
     tartalomajánló
    0.81
    RenderAtEndOf
    0.77
     MainAxisSize
    0.74
    MockMvc
    0.67
    UIControlState
    0.66
     typelib
    0.63
     himo
    0.63
    PickerController
    0.62
     дописавши
    0.62
    Activations Density 0.204%

    No Known Activations