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. 0
    Prev
    Next
    INDEX
    Explanations

    references to age

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

    "age" or variants

    np_acts-logits-general · gemini-2.0-flash

    age of

    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
     ostavi
    -0.69
    Vinc
    -0.65
     فريبيس
    -0.62
    $).
    -0.62
    Geplaatst
    -0.61
    WebControls
    -0.60
    ?>">
    -0.60
    ürlich
    -0.59
    ricio
    -0.58
    BDL
    -0.57
    POSITIVE LOGITS
     age
    1.06
     Age
    1.02
     AGE
    0.93
    Age
    0.91
    getAge
    0.91
     getAge
    0.85
     ages
    0.80
     Ages
    0.80
     edad
    0.75
    Ages
    0.73
    Activations Density 0.099%

    No Known Activations