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. 19-GEMMASCOPE-RES-16K
    6. 11246
    Prev
    Next
    INDEX
    Explanations

    references to software licenses and legal requirements associated with software

    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
    UserScript
    -0.60
     bakgrund
    -0.55
     vosotros
    -0.49
     către
    -0.48
    ydı
    -0.46
    Descripció
    -0.46
     soeur
    -0.46
     prieten
    -0.46
     Мексичка
    -0.45
    idazole
    -0.45
    POSITIVE LOGITS
     EconPapers
    0.77
    Personensuche
    0.69
    styleUrls
    0.60
    \}\\
    0.58
     Paglinawan
    0.58
    ])).
    0.54
    CustomAttributes
    0.54
    ENZA
    0.54
    OGND
    0.54
     onCreateView
    0.54
    Activations Density 0.061%

    No Known Activations