© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 11240
    Prev
    Next
    INDEX
    Explanations

    specific nouns and their corresponding attributes or actions in complex contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    큼
    -0.49
     Kluwer
    -0.42
     تانيه
    -0.41
     Greenland
    -0.41
     العنوان
    -0.41
    LogLevel
    -0.41
    ⚭
    -0.40
    reszcie
    -0.40
    tion
    -0.40
    entityManager
    -0.39
    POSITIVE LOGITS
    SourceChecksum
    0.86
     invokingState
    0.83
    ContentAsync
    0.69
    :✨
    0.65
    httphttps
    0.64
    DockStyle
    0.63
    UserScript
    0.62
    CppMethod
    0.61
    ьаж
    0.61
     للاسماء
    0.61
    Activations Density 3.187%

    No Known Activations