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. 2-GEMMASCOPE-RES-16K
    6. 14940
    Prev
    Next
    INDEX
    Explanations

    references to specific pages in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HasAnnotation
    -0.63
    рт
    -0.57
    ástica
    -0.55
    HostException
    -0.53
     glyphicon
    -0.50
     natale
    -0.47
     rapporti
    -0.47
     blauwe
    -0.47
    ği
    -0.46
     droits
    -0.46
    POSITIVE LOGITS
    Pages
    2.71
     pages
    2.63
     Pages
    2.56
    pages
    2.51
     PAGES
    2.15
    PAGES
    1.92
     páginas
    1.55
    Páginas
    1.45
     pagine
    1.26
    Seiten
    1.15
    Activations Density 0.097%

    No Known Activations