© 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. 8-GEMMASCOPE-RES-16K
    11. 6371
    Prev
    Next
    INDEX
    Explanations

    terms related to skeletal structures and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_8/width_16k/average_l0_99
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wapV
    -0.60
     Wiktionnaire
    -0.59
    transQ
    -0.55
    曖昧さ回避
    -0.54
    ->___
    -0.54
    StoryboardSegue
    -0.51
    
    -0.50
     MainAxisSize
    -0.50
    essoa
    -0.50
    discharge
    -0.49
    POSITIVE LOGITS
     structural
    0.69
     skeleton
    0.64
     esqueleto
    0.64
    Structural
    0.64
     estructural
    0.62
     Structural
    0.60
    structural
    0.60
     skeletal
    0.57
    框架
    0.56
     frame
    0.55
    Activations Density 0.379%

    No Known Activations