© 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. 15-GEMMASCOPE-RES-16K
    6. 12657
    Prev
    Next
    INDEX
    Explanations

    the presence of specific programming class structures and elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SharedDtor
    -0.62
    IsMutable
    -0.59
    omitempty
    -0.58
     unknownFields
    -0.57
     AppDelegate
    -0.57
    webElement
    -0.56
    UnusedPrivate
    -0.54
    NgModule
    -0.53
     <>",
    -0.53
     oprot
    -0.53
    POSITIVE LOGITS
    出版年
    0.54
    attori
    0.52
     perpétu
    0.49
    {}/
    0.48
    ogno
    0.48
    Ikus
    0.48
    发表于
    0.47
    ^@
    0.47
    請繼續往下閱讀
    0.47
     cherchés
    0.47
    Activations Density 0.073%

    No Known Activations