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. 18-GEMMASCOPE-RES-16K
    6. 5098
    Prev
    Next
    INDEX
    Explanations

    phrases and details regarding age, particularly the mention of years or ages of individuals

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

    Ages expressed in years

    np_acts-logits-general · gemini-2.0-flash

    years old

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.91
    NameInMap
    -0.73
     يتيمه
    -0.70
    :✨
    -0.68
     TextAppearance
    -0.67
     years
    -0.67
    Datuak
    -0.66
     Roskov
    -0.65
    AutoScaleMode
    -0.65
     YEARS
    -0.65
    POSITIVE LOGITS
     old
    1.19
    old
    1.09
    olds
    0.83
    Old
    0.82
     olds
    0.82
    OLD
    0.78
     Old
    0.78
     OLD
    0.76
    老
    0.68
     oude
    0.63
    Activations Density 0.123%

    No Known Activations