Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 4968
    Prev
    Next
    INDEX
    Explanations

    lines of code related to color definitions and styles in CSS

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     CanadaChoose
    -0.96
    StoryboardSegue
    -0.96
    تقاوى
    -0.93
     незавершена
    -0.91
    rungsseite
    -0.89
    存于互联网档案馆
    -0.87
    Personensuche
    -0.84
    verwijspagina
    -0.84
     createSprite
    -0.84
    __':
    
    -0.84
    POSITIVE LOGITS
     Fonseca
    0.57
     Thema
    0.57
     hielo
    0.54
    onymie
    0.50
    rigin
    0.50
    UrlResolution
    0.50
    Regions
    0.49
    region
    0.48
     préférable
    0.48
     dens
    0.48
    Activations Density 0.034%

    No Known Activations