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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 15-GEMMASCOPE-RES-16K
    6. 2827
    Prev
    Next
    INDEX
    Explanations

    references to time, specifically the term 'year' and related timeframes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pinulongan
    -0.84
    ,
    
    
    -0.72
    DotNetBar
    -0.70
    IntoConstraints
    -0.68
    dbc
    -0.67
    xFFFFFFFF
    -0.67
     useDispatch
    -0.66
    chis
    -0.65
    );
    
    
    -0.65
     Intelli
    -0.65
    POSITIVE LOGITS
     year
    1.59
     Year
    1.45
    year
    1.43
     YEAR
    1.43
    Year
    1.36
     years
    1.32
    YEAR
    1.31
    years
    1.18
     Years
    1.10
     année
    1.09
    Activations Density 0.121%

    No Known Activations