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-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 13100
    Prev
    Next
    INDEX
    Explanations

    Java classes and methods related to date manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mules
    -0.33
     Henk
    -0.33
     mendengarkan
    -0.32
    addresses
    -0.31
    listening
    -0.31
     Policía
    -0.30
    loit
    -0.30
    جمعیت
    -0.30
     Estadística
    -0.30
    quehanna
    -0.29
    POSITIVE LOGITS
     calendar
    1.56
     Calendar
    1.45
    Calendar
    1.30
     calendars
    1.30
     dates
    1.25
    calendar
    1.21
     CALENDAR
    1.20
     Calend
    1.19
     calendario
    1.18
     Dates
    1.16
    Activations Density 0.432%

    No Known Activations