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. 16-GEMMASCOPE-RES-16K
    6. 14909
    Prev
    Next
    INDEX
    Explanations

    references to aging or things labeled as "old."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "old" before other words

    np_acts-logits-general · gemini-2.0-flash

    old concepts and items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     possano
    -0.67
     hilsen
    -0.65
    agoza
    -0.64
    drawable
    -0.63
     Praze
    -0.62
     Himo
    -0.62
    ViewFeatures
    -0.62
    esgue
    -0.61
    췄
    -0.61
     butterflies
    -0.60
    POSITIVE LOGITS
     fashioned
    1.23
     OLD
    1.06
     old
    1.04
     Old
    1.01
    Old
    0.95
     vieux
    0.87
    fashioned
    0.85
     vieja
    0.81
     vecchio
    0.81
     viejo
    0.80
    Activations Density 0.064%

    No Known Activations