© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 332
    Prev
    Next
    INDEX
    Explanations

    the merging of different ideas, elements, or themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '\\;'
    -0.71
     Extragalactic
    -0.61
     فريبيس
    -0.61
    الإنجليزية
    -0.58
     Económica
    -0.57
    Rüyada
    -0.56
     diſt
    -0.56
    lorette
    -0.56
    BeginContext
    -0.55
    asgi
    -0.54
    POSITIVE LOGITS
     combining
    1.09
     combines
    1.09
     combine
    0.99
    Combining
    0.99
     Combining
    0.95
     combined
    0.90
     blends
    0.89
     mixes
    0.87
     merges
    0.87
    combine
    0.86
    Activations Density 0.438%

    No Known Activations