© 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. 9218
    Prev
    Next
    INDEX
    Explanations

    references to the sun and its various states or actions

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

    the sun or solar activity

    np_acts-logits-general · gemini-2.0-flash

    sun and solar concepts

    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
    hala
    -0.56
     Schalke
    -0.55
    zegovina
    -0.55
     configureStore
    -0.55
    Zack
    -0.52
     Ries
    -0.52
    ritsar
    -0.51
     Vy
    -0.50
    quanti
    -0.50
    ()?.
    -0.50
    POSITIVE LOGITS
     SUN
    1.19
     suns
    1.18
     Sun
    1.16
    SUN
    1.11
    Sun
    1.11
     Suns
    1.11
     sun
    1.04
    sun
    1.03
    Suns
    0.94
     sunshine
    0.93
    Activations Density 0.138%

    No Known Activations