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

    Neuronpedia

    APICircuit 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. 12-GEMMASCOPE-RES-16K
    6. 5120
    Prev
    Next
    INDEX
    Explanations

    terms related to age and generational differences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atouille
    -0.72
    XmlAccessType
    -0.63
    esgue
    -0.55
    orgs
    -0.55
    migrationBuilder
    -0.52
    IGraphics
    -0.52
    Dibrom
    -0.50
    /*
    -0.50
    uette
    -0.49
    httphttps
    -0.49
    POSITIVE LOGITS
     age
    1.37
     edad
    1.03
     âge
    1.01
     Age
    1.01
     aged
    1.00
    Age
    0.98
     getAge
    0.95
     aging
    0.94
     ageing
    0.94
     ages
    0.93
    Activations Density 0.463%

    No Known Activations