© 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. 3-GEMMASCOPE-RES-16K
    11. 8282
    Prev
    Next
    INDEX
    Explanations

    numerical or quantitative data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     graduación
    -0.31
     Sociales
    -0.31
     tarihinde
    -0.30
     distinción
    -0.30
     acusa
    -0.29
     divisão
    -0.29
     senere
    -0.29
     cór
    -0.29
     scorso
    -0.28
     condena
    -0.28
    POSITIVE LOGITS
     kasarigan
    1.02
     betweenstory
    0.82
    adaptiveStyles
    0.73
    Personendaten
    0.72
    تقاوى
    0.69
    
    0.66
     Италијани
    0.65
    RuleContext
    0.65
    Vidite
    0.63
    ThemeOverlay
    0.61
    Activations Density 0.427%

    No Known Activations