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. 3-GEMMASCOPE-RES-16K
    6. 8184
    Prev
    Next
    INDEX
    Explanations

    phrases related to time durations, particularly in the context of months and hours

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalTable
    -0.63
     vettoriale
    -0.62
     useDispatch
    -0.61
    Население
    -0.60
    verifyException
    -0.60
    Obrázky
    -0.60
    SqlClient
    -0.59
     Deber
    -0.59
     estekak
    -0.57
     diritti
    -0.57
    POSITIVE LOGITS
     months
    2.05
     Months
    1.70
    months
    1.69
    Months
    1.49
     MONTHS
    1.48
     meses
    1.34
     years
    1.34
     Monate
    1.29
     maanden
    1.12
     Monaten
    1.11
    Activations Density 0.072%

    No Known Activations