© 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-2-9B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 12607
    Prev
    Next
    INDEX
    Explanations

    terms related to definitions and descriptions of figures and representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ब्रेकडाउन
    -0.64
    ScopeManager
    -0.64
     kaarangay
    -0.63
     мәкал
    -0.56
    
    -0.56
    IsMutable
    -0.54
     GenerationType
    -0.53
     nakalista
    -0.53
    Manbalar
    -0.52
    WithIOException
    -0.52
    POSITIVE LOGITS
     informée
    0.36
     offering
    0.33
    insee
    0.32
    xtures
    0.32
    Jawaban
    0.32
    Jawab
    0.30
     membran
    0.29
    örm
    0.29
     attendance
    0.28
     figur
    0.28
    Activations Density 1.059%

    No Known Activations