© 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. 5371
    Prev
    Next
    INDEX
    Explanations

    phrases expressing future possibilities or predictions

    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
     Paglinawan
    -0.63
    Stayed
    -0.57
     obliquely
    -0.53
    事前に
    -0.53
     geblieben
    -0.52
    StringVar
    -0.52
     мәкал
    -0.51
    !("{}",
    -0.51
     BoxDecoration
    -0.51
    ParallelGroup
    -0.50
    POSITIVE LOGITS
     will
    0.61
    有一天
    0.55
    原始内容存档于
    0.54
    findpost
    0.54
     hopefully
    0.52
     reach
    0.51
     Infórmanos
    0.51
     rid
    0.51
     hoff
    0.50
    Hozzáférés
    0.50
    Activations Density 0.197%

    No Known Activations