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. 12-GEMMASCOPE-RES-16K
    6. 2831
    Prev
    Next
    INDEX
    Explanations

    discussions about the regulation and impact of medications and treatments for health conditions

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

    Finds words that signal changes or increases in measured outcomes (e.g., increased, promoted, enhanced, rising use or production) in scientific/medical contexts.

    oai_token-act-pair · gpt-5-miniTriggered by @phamvanluong2003
    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
    تفصیلات
    -0.53
     Suff
    -0.46
    ierende
    -0.46
     Pins
    -0.43
    ಗ
    -0.42
    mbggenerated
    -0.42
    chau
    -0.42
    humidité
    -0.42
    TemporalType
    -0.42
     donkey
    -0.41
    POSITIVE LOGITS
     kaarangay
    0.66
    rrggbb
    0.56
    ReusableCell
    0.55
    GEBURTSDATUM
    0.55
    poň
    0.55
    kloped
    0.54
    NameInMap
    0.54
     للمعارف
    0.53
    zbęd
    0.53
    المشاركات
    0.52
    Activations Density 0.861%

    No Known Activations