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. 4761
    Prev
    Next
    INDEX
    Explanations

    specific geographical locations and terms related to environmental features and biological assessments

    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
     cervello
    -0.69
    kili
    -0.65
     zerst
    -0.63
    иск
    -0.63
    Funciones
    -0.62
    illard
    -0.62
     selva
    -0.62
     כן
    -0.61
     Weiss
    -0.60
     Ferri
    -0.60
    POSITIVE LOGITS
    Geplaatst
    1.04
     Walkover
    0.94
     Мексичка
    0.94
    parsedMessage
    0.90
     '{@
    0.89
    lapsingToolbar
    0.89
     useAppContext
    0.87
    NameInMap
    0.87
     OFDb
    0.85
    ResumeLayout
    0.85
    Activations Density 1.992%

    No Known Activations