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. 15-GEMMASCOPE-RES-16K
    6. 8737
    Prev
    Next
    INDEX
    Explanations

    phrases related to yearly reflections and future goals

    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
    Personendaten
    -0.58
     Italijani
    -0.51
     المعيارى
    -0.51
    Спасылкі
    -0.46
    yal
    -0.46
    isEmail
    -0.46
     минуты
    -0.46
    
    -0.46
    }%
    -0.45
    ALIA
    -0.45
    POSITIVE LOGITS
    RegressionTest
    0.80
     calendar
    0.71
    MigrationBuilder
    0.67
     year
    0.67
     året
    0.65
    ViewFeatures
    0.63
    Autoritní
    0.60
     OFDb
    0.60
     année
    0.58
     Pend
    0.57
    Activations Density 0.224%

    No Known Activations