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. 3-GEMMASCOPE-RES-16K
    6. 10292
    Prev
    Next
    INDEX
    Explanations

    concepts related to the quality of life, particularly in health contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Administrativna
    -0.91
    SequentialGroup
    -0.77
    Демографія
    -0.76
    __*/
    -0.75
    Personensuche
    -0.74
     compartida
    -0.74
    QMetaType
    -0.74
    kháu
    -0.72
    atrician
    -0.72
     Italijani
    -0.70
    POSITIVE LOGITS
    stro
    0.52
    TagMode
    0.52
     arti
    0.52
    行
    0.50
    այ
    0.50
    parseDouble
    0.47
    ristan
    0.47
    tit
    0.46
     tiếp
    0.45
    ocer
    0.45
    Activations Density 1.132%

    No Known Activations