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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 1002
    Prev
    Next
    INDEX
    Explanations

    mentions of the day "Monday."

    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
     Mosley
    -0.71
     CURIAM
    -0.70
     onCancelled
    -0.68
    sizeCache
    -0.68
    complexType
    -0.66
     DMSO
    -0.64
    onOptions
    -0.62
    viewDidLoad
    -0.61
    alanta
    -0.61
     Frey
    -0.61
    POSITIVE LOGITS
     Monday
    1.53
    Monday
    1.36
     monday
    1.30
     MONDAY
    1.24
    MONDAY
    1.23
     Mondays
    1.05
     lundi
    1.05
    Lunes
    1.04
    monday
    1.04
     lunes
    1.01
    Activations Density 0.058%

    No Known Activations