© 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. 19-GEMMASCOPE-RES-16K
    6. 17
    Prev
    Next
    INDEX
    Explanations

    CSS font properties related to font size, weight, and family

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/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.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sortant
    -0.57
     élus
    -0.56
     préciser
    -0.55
     rejoindre
    -0.53
     okuyayım
    -0.53
     EconPapers
    -0.53
    onViewCreated
    -0.53
     umana
    -0.52
     transferencia
    -0.52
    rull
    -0.52
    POSITIVE LOGITS
     FONT
    1.32
     font
    1.29
     Font
    1.25
     fonts
    1.22
     Fonts
    1.18
    font
    1.17
    Font
    1.07
    fonts
    0.98
     Fontana
    0.94
    Fonts
    0.93
    Activations Density 0.046%

    No Known Activations