© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 675
    Prev
    Next
    INDEX
    Explanations

    references to "other" or "others" in various 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
     Thousands
    -0.58
    Lin
    -0.56
     Walpole
    -0.54
    flé
    -0.53
     gigabyte
    -0.53
     πολλά
    -0.52
    anskje
    -0.52
    Thousands
    -0.52
     gh
    -0.52
    出版年
    -0.52
    POSITIVE LOGITS
    enumii
    0.75
     Normdatei
    0.73
    PreferredItem
    0.73
    contentLoaded
    0.70
    rungsseite
    0.68
    ftagPool
    0.68
    EDEFAULT
    0.67
    ChildScrollView
    0.67
    Datuak
    0.66
     ویکی‌پدیای
    0.66
    Activations Density 0.069%

    No Known Activations