© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 7891
    Prev
    Next
    INDEX
    Explanations

    instances of the word "later" indicating a passage of time

    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
    MemoryWarning
    -0.70
    stdc
    -0.68
    chise
    -0.63
    venido
    -0.63
    ScopeManager
    -0.63
    PasswordEncoder
    -0.63
    CppMethod
    -0.62
     {
    
    
    -0.62
    %)$
    -0.62
    Égypte
    -0.61
    POSITIVE LOGITS
     later
    3.48
     Later
    3.02
    later
    3.01
    Later
    2.98
     LATER
    2.73
     später
    2.37
     senere
    2.11
     späteren
    2.06
     senare
    2.04
     afterwards
    1.97
    Activations Density 0.067%

    No Known Activations