© 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. 2432
    Prev
    Next
    INDEX
    Explanations

    references to cultural festivals and their associated calendars

    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
     viewDidLoad
    -0.59
    errHandler
    -0.52
    MemoryWarning
    -0.52
     ModelExpression
    -0.49
    DialogContent
    -0.49
     للاسماء
    -0.49
     kaynağından
    -0.49
    odrome
    -0.49
    \{\\
    -0.49
    friday
    -0.48
    POSITIVE LOGITS
     year
    1.80
    year
    1.39
     YEAR
    1.38
     Year
    1.36
    Year
    1.32
     året
    1.25
     seasons
    1.20
     año
    1.19
    YEAR
    1.17
     season
    1.13
    Activations Density 0.158%

    No Known Activations